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

    Neuronpedia

    INDEX
    Explanations

    no matter what

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    在
    1.27
    も
    1.02
    ও
    0.92
    도
    0.92
    에
    0.86
    '
    0.73
    들이
    0.73
    발
    0.73
     σε
    0.71
     Leafs
    0.70
    POSITIVE LOGITS
    ت
    0.79
     on
    0.73
    িয়া
    0.72
    ion
    0.70
    ressing
    0.70
     l
    0.70
    OD
    0.70
     elegante
    0.70
     at
    0.69
    eto
    0.68
    Act Density 0.000%

    No Known Activations