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

    Neuronpedia

    INDEX
    Explanations

    hand

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     řek
    -0.07
     BOT
    -0.07
    onclick
    -0.06
     given
    -0.06
    �
    -0.06
    _placement
    -0.06
    鉄道
    -0.06
    ीं
    -0.06
     dog
    -0.06
    Fake
    -0.06
    POSITIVE LOGITS
    essa
    0.07
    ,text
    0.07
     PSI
    0.07
    ORDER
    0.07
    бра
    0.06
    gradation
    0.06
     України
    0.06
     Amerikan
    0.06
     Diane
    0.06
    sanitize
    0.06
    Act Density 0.010%

    No Known Activations