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

    Neuronpedia

    INDEX
    Explanations

    java class inheritance or flutter widgets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    าะ
    0.54
    atherine
    0.53
    ड्यूल
    0.52
    cie
    0.52
     végétale
    0.52
    ється
    0.51
     કરીને
    0.51
    hrer
    0.50
    ření
    0.50
    haut
    0.50
    POSITIVE LOGITS
    :
    0.78
    Trust
    0.70
     Tranqu
    0.68
    '
    0.66
    us
    0.65
     You
    0.65
    说
    0.64
    Transactions
    0.64
    Payout
    0.64
    Defer
    0.61
    Act Density 0.000%

    No Known Activations