Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    instances of memory management and pointer operations in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code snippets with ampersands and specific tokens after

    np_acts-logits-general · gemini-2.0-flash

    cuda, device, parse, thread, implementation, vendor, account

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     and
    -0.61
     also
    -0.60
    NSIndexPath
    -0.60
     O
    -0.59
     R
    -0.57
     US
    -0.57
     '
    -0.56
     
    -0.56
    </strong>
    -0.56
     A
    -0.55
    POSITIVE LOGITS
     étoient
    1.15
     avoient
    1.08
     feroit
    1.04
    InjectAttribute
    1.01
     CreateTagHelper
    1.01
    enumi
    1.01
     auroit
    0.99
     autorytatywna
    0.94
    sizeCache
    0.92
     ainfi
    0.88
    Act Density 0.067%

    No Known Activations