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

    Neuronpedia

    INDEX
    Explanations

    data/variables

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Sum
    -0.07
     možné
    -0.06
     صنایع
    -0.06
     βρί
    -0.06
    ，每
    -0.06
    ;q
    -0.06
    izada
    -0.06
    <Menu
    -0.06
     Eug
    -0.06
     requer
    -0.06
    POSITIVE LOGITS
    .into
    0.07
     flo
    0.07
    lico
    0.06
    bose
    0.06
    _nn
    0.06
     newsp
    0.06
     cerebral
    0.06
     Emit
    0.06
     cigarette
    0.06
    _lst
    0.06
    Act Density 0.083%

    No Known Activations