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

    Neuronpedia

    INDEX
    Explanations

    financial charges and fees

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     it
    1.20
    (
    0.91
    ਰ
    0.83
    ീകരണ
    0.82
     OCD
    0.79
     I
    0.78
     an
    0.78
    رے
    0.77
     IDEA
    0.77
    ियों
    0.75
    POSITIVE LOGITS
    and
    1.16
     fees
    1.09
    us
    0.93
     fee
    0.93
    ud
    0.91
                   
    0.86
    а
    0.86
    0
    0.84
     FEES
    0.81
    Fees
    0.81
    Act Density 0.005%

    No Known Activations