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

    Neuronpedia

    INDEX
    Explanations

    patterns in programming syntax and logical constructs within code snippets

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

    political events claims

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddHtmlAttribute
    -0.33
    ///</
    -0.31
     control
    -0.29
     care
    -0.29
    kissen
    -0.29
     train
    -0.28
     MAH
    -0.28
     cach
    -0.28
     kaarangay
    -0.28
     об
    -0.27
    POSITIVE LOGITS
    BeginContext
    0.61
     surla
    0.59
    Sucesor
    0.58
     pulumi
    0.57
    RTEX
    0.57
    果た
    0.55
     Glied
    0.54
    twimg
    0.52
    dersfield
    0.52
    RemoveField
    0.50
    Act Density 0.218%

    No Known Activations