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

    Neuronpedia

    INDEX
    Explanations

    file paths and code syntax in programming contexts

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

    file paths or URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.81
    HandlerContext
    -0.63
     createSprite
    -0.63
    ernalia
    -0.59
    <unused23>
    -0.59
    <unused14>
    -0.59
    <unused41>
    -0.59
    <unused52>
    -0.59
    <unused28>
    -0.59
    <unused3>
    -0.59
    POSITIVE LOGITS
     class
    0.31
     cref
    0.30
     amarillas
    0.29
     chez
    0.29
     subclass
    0.29
     attiv
    0.28
    ById
    0.27
    EndGlobal
    0.27
     delan
    0.27
    ByPrimaryKey
    0.27
    Act Density 0.020%

    No Known Activations