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

    Neuronpedia

    INDEX
    Explanations

    programming constructs and annotations related to defining classes and data structures

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

    extern "C", "//" comments, "user" prefix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AsUp
    -0.74
    AnimationsModule
    -0.63
    msgSender
    -0.62
    󠁴
    -0.61
    tonode
    -0.61
     snippetHide
    -0.60
    IsContent
    -0.59
     betweenstory
    -0.57
    ագրություններ
    -0.57
    PerformLayout
    -0.56
    POSITIVE LOGITS
    derive
    0.60
     derived
    0.49
     derive
    0.38
    derived
    0.36
     déri
    0.36
    ArgumentParser
    0.35
     derives
    0.34
     Alban
    0.34
     deriv
    0.33
     serde
    0.33
    Act Density 0.003%

    No Known Activations