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

    Neuronpedia

    INDEX
    Explanations

    references to individual items or units within a larger set

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

    one of each

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     czasem
    -0.36
    niosek
    -0.35
    strain
    -0.35
     gondola
    -0.35
    citep
    -0.35
    Tetrach
    -0.35
     sometimes
    -0.35
    resort
    -0.33
     gopro
    -0.33
     StatefulWidget
    -0.33
    POSITIVE LOGITS
     typelib
    0.57
     kaarangay
    0.55
    IntoConstraints
    0.51
    sizeCache
    0.50
     mergeFrom
    0.49
    ParallelGroup
    0.49
    transQ
    0.47
     protoimpl
    0.47
     utafitiHapana
    0.47
    BeginInit
    0.45
    Act Density 0.021%

    No Known Activations