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

    Neuronpedia

    INDEX
    Explanations

    озв

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     evolve
    -0.06
     capitalize
    -0.06
     evaluating
    -0.06
     launching
    -0.06
     trace
    -0.06
     Shoot
    -0.06
     Women
    -0.06
     orbits
    -0.06
    >Data
    -0.06
    Þ
    -0.06
    POSITIVE LOGITS
    _USERNAME
    0.08
    ARRANT
    0.07
     전문
    0.07
    .mp
    0.07
    =l
    0.07
     także
    0.07
    ิลป
    0.07
     randomNumber
    0.06
    (rect
    0.06
     POSS
    0.06
    Act Density 0.001%

    No Known Activations