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

    Neuronpedia

    INDEX
    Explanations

    access to social benefits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wavefront
    1.36
    buscar
    1.27
     vectorized
    1.26
     Initialization
    1.22
    検証
    1.20
    ان
    1.17
     অনুয
    1.17
    如下
    1.16
    ş
    1.14
    LinearLayout
    1.13
    POSITIVE LOGITS
     RSV
    1.06
    iker
    1.04
     arrivent
    1.04
    เงิน
    1.03
    orer
    1.02
    मग
    1.01
    arily
    1.01
     इसकी
    1.01
    ಂದು
    0.99
    म
    0.99
    Act Density 0.000%

    No Known Activations