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

    Neuronpedia

    INDEX
    Explanations

    control structures and conditional statements in programming code

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

    while loops and empty checks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AnimationsModule
    -0.75
     Jefus
    -0.61
     desmotivaciones
    -0.61
     Geiſt
    -0.59
    TypedDataSet
    -0.59
    IntoConstraints
    -0.59
    <unused43>
    -0.58
    𑄮
    -0.58
    <unused16>
    -0.58
    <unused14>
    -0.58
    POSITIVE LOGITS
     «
    0.33
     ni
    0.33
    yto
    0.33
     sie
    0.32
     te
    0.31
     снима
    0.31
     salvo
    0.31
     pri
    0.31
     hom
    0.30
    Pri
    0.30
    Act Density 0.002%

    No Known Activations