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

    Neuronpedia

    INDEX
    Explanations

    I

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     BaseService
    -0.07
    twor
    -0.07
     cler
    -0.07
     Sel
    -0.07
     ActiveRecord
    -0.07
    े�
    -0.06
    낑
    -0.06
     пример
    -0.06
    \Abstract
    -0.06
    [,]
    -0.06
    POSITIVE LOGITS
    _SM
    0.07
    ша
    0.07
     communicates
    0.07
    _supported
    0.07
     Spread
    0.07
    宣讲
    0.07
     skincare
    0.07
    棄
    0.06
     Sw
    0.06
    瞽
    0.06
    Act Density 0.000%

    No Known Activations