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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nave
    -0.07
    (timer
    -0.07
    Ns
    -0.07
    uted
    -0.06
     Goodman
    -0.06
    ogenesis
    -0.06
    .fft
    -0.06
    ared
    -0.06
     Religious
    -0.06
    /games
    -0.06
    POSITIVE LOGITS
    uluğ
    0.07
     sustained
    0.07
    !!!!!
    0.06
     elbows
    0.06
    best
    0.06
     Glouce
    0.06
    irtual
    0.06
     remodel
    0.06
     sucked
    0.06
    regist
    0.06
    Act Density 0.012%

    No Known Activations