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

    Neuronpedia

    INDEX
    Explanations

    financial default risk

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    но
    0.92
    е
    0.73
    IX
    0.72
    то
    0.68
    и
    0.67
    İN
    0.66
    店の
    0.65
     ناحيه
    0.65
    IED
    0.64
    ана
    0.64
    POSITIVE LOGITS
     vals
    0.73
     defaulting
    0.65
    了一个
    0.54
    c
    0.54
    גר
    0.53
    dling
    0.53
    ್ದ
    0.52
    ంబేద్కర్
    0.52
     bylaws
    0.52
     sprays
    0.52
    Act Density 0.002%

    No Known Activations