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

    Neuronpedia

    INDEX
    Explanations

    vulnerabilities and winning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     etcétera
    0.51
    <unused2221>
    0.47
    －
    0.46
    さまざまな
    0.45
     ­
    0.44
     —
    0.42
    ）（
    0.42
    ）
    0.42
     yüzde
    0.42
    ־
    0.42
    POSITIVE LOGITS
     folks
    0.82
     সাথে
    0.72
     amongst
    0.71
     মোঃ
    0.70
     নেবার
    0.70
     skall
    0.68
     bbq
    0.67
     kinda
    0.66
     দাবী
    0.66
     surprisingly
    0.65
    Act Density 0.001%

    No Known Activations