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

    Neuronpedia

    INDEX
    Explanations

    expressions of respect and evaluation of behavior

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

    states or conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     createSprite
    -0.50
     razonable
    -0.42
    ItemBackground
    -0.41
    orology
    -0.40
     kereszt
    -0.39
     introducción
    -0.39
    ----</
    -0.39
     estrictamente
    -0.38
    êque
    -0.38
     chaleco
    -0.37
    POSITIVE LOGITS
    ACHUSET
    0.44
    Trayectoria
    0.43
    uxxxx
    0.42
    tamento
    0.41
    Toponymie
    0.40
     ביט
    0.40
     Scarborough
    0.40
    <?
    0.38
    cellence
    0.37
    TagMode
    0.37
    Act Density 0.331%

    No Known Activations