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

    Neuronpedia

    INDEX
    Explanations

    it's followed by describing words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ों
    0.94
    ۔
    0.81
     которого
    0.79
     (=
    0.78
    ের
    0.78
    are
    0.77
    ®,
    0.76
     (\"
    0.75
    之类的
    0.74
    වල
    0.73
    POSITIVE LOGITS
    ’
    1.76
    '
    1.67
    inerary
    1.29
     beho
    1.15
    asca
    1.07
    INER
    1.04
     doesn
    1.04
    iner
    1.02
     happens
    1.01
     rained
    1.00
    Act Density 0.539%

    No Known Activations