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

    Neuronpedia

    INDEX
    Explanations

    table columns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ’
    0.88
    ,
    0.83
    ра
    0.77
     compartments
    0.75
    闓
    0.74
    )"
    0.68
     pants
    0.67
     as
    0.66
     emblems
    0.66
     kalangan
    0.65
    POSITIVE LOGITS
    1
    1.11
    m
    1.09
     for
    1.06
    ní
    0.99
    is
    0.96
    mán
    0.93
    ang
    0.92
    ról
    0.91
    é
    0.88
     by
    0.84
    Act Density 0.062%

    No Known Activations