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

    Neuronpedia

    INDEX
    Explanations

    amount won

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    S
    0.87
    H
    0.84
    가
    0.82
    us
    0.80
    being
    0.76
    ch
    0.75
    a
    0.73
    ;
    0.72
    -
    0.71
    ,
    0.71
    POSITIVE LOGITS
    <unused2130>
    1.36
    <unused2125>
    1.26
    不仅
    1.20
     zarówno
    1.18
    繍
    1.17
     erroneous
    1.15
    <unused2137>
    1.15
     antibacterial
    1.14
    ків
    1.13
    <unused1794>
    1.13
    Act Density 0.000%

    No Known Activations