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

    Neuronpedia

    INDEX
    Explanations

    game theory

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    wanted
    -0.09
    ARD
    -0.08
     oração
    -0.08
     cruise
    -0.08
    .wave
    -0.08
     recognized
    -0.07
    brew
    -0.07
    veral
    -0.07
     refrigeration
    -0.07
    _Adjustor
    -0.07
    POSITIVE LOGITS
     incumbent
    0.10
    _moves
    0.10
     Players
    0.09
     игроков
    0.09
     размещ
    0.09
     Dumb
    0.09
     खिलाड़ियों
    0.09
     cartas
    0.09
    _INITIAL
    0.08
     Moves
    0.08
    Act Density 0.026%

    No Known Activations