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

    Neuronpedia

    INDEX
    Explanations

    hands

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SPAN
    -0.08
    表达
    -0.06
     SCREEN
    -0.06
     praised
    -0.06
    صغر
    -0.06
    フラ
    -0.06
    JOR
    -0.06
    bih
    -0.06
     Kensington
    -0.06
    第二节
    -0.06
    POSITIVE LOGITS
    狐狸
    0.08
    _party
    0.07
    诱惑
    0.07
     בידי
    0.06
     intuitive
    0.06
     elapsed
    0.06
     hoses
    0.06
    ဈ
    0.06
    usive
    0.06
    _er
    0.06
    Act Density 0.014%

    No Known Activations