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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     shots
    -0.07
     Amateur
    -0.07
    Actual
    -0.07
     Gala
    -0.07
     diplomatic
    -0.06
     Lieutenant
    -0.06
     Winner
    -0.06
    .Registry
    -0.06
    르
    -0.06
    accumulator
    -0.06
    POSITIVE LOGITS
    ulence
    0.06
     вваж
    0.06
     ισχ
    0.06
    _sep
    0.06
    να
    0.06
    реб
    0.06
    341
    0.06
    ื
    0.06
    rapy
    0.06
    285
    0.06
    Act Density 0.006%

    No Known Activations