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

    Neuronpedia

    INDEX
    Explanations

    schema

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fetish
    -0.07
    ıc
    -0.07
    FO
    -0.07
     outrage
    -0.07
    �
    -0.07
    铠
    -0.07
     nurs
    -0.07
    かけ
    -0.07
    HB
    -0.07
    :l
    -0.07
    POSITIVE LOGITS
    …↵↵↵
    0.07
    (completion
    0.07
    mnop
    0.07
    𝄅
    0.07
    )((
    0.07
     Cro
    0.06
    챃
    0.06
     posY
    0.06
    owie
    0.06
    getMethod
    0.06
    Act Density 0.004%

    No Known Activations