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

    Neuronpedia

    INDEX
    Explanations

    Actions and methods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     玩家
    -0.08
    _broadcast
    -0.07
    72
    -0.07
    :create
    -0.07
     implement
    -0.07
    +.
    -0.06
    lead
    -0.06
    通常
    -0.06
    Europe
    -0.06
     Her
    -0.06
    POSITIVE LOGITS
     Hort
    0.07
     junge
    0.07
    ephir
    0.06
     ipad
    0.06
     scarf
    0.06
     counting
    0.06
    (si
    0.06
    _uv
    0.06
     그림
    0.06
     Tatto
    0.06
    Act Density 0.092%

    No Known Activations