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

    Neuronpedia

    INDEX
    Explanations

    is a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     мои
    -2.44
     всички
    -2.30
     zobac
    -2.20
     большие
    -2.20
     två
    -2.13
    gorro
    -2.13
     negociaciones
    -2.03
    噠
    -2.02
     wszyscy
    -2.00
    偸
    -1.97
    POSITIVE LOGITS
     isn
    1.90
     find
    1.87
    на
    1.82
     a
    1.79
     L
    1.79
     England
    1.77
     answer
    1.77
     September
    1.74
     amount
    1.74
     R
    1.74
    Act Density 0.359%

    No Known Activations