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

    Neuronpedia

    INDEX
    Explanations

    critical severity CVE CVSS

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    扃
    0.50
     LongNumber
    0.49
     சோதனை
    0.49
    踟
    0.48
    踌
    0.48
    Lä
    0.47
    袢
    0.46
    㹮
    0.46
     orderService
    0.43
     Maugin
    0.43
    POSITIVE LOGITS
     severity
    0.54
    affected
    0.53
    affect
    0.53
     affected
    0.51
     CVE
    0.50
     Severity
    0.49
     software
    0.48
    severity
    0.47
    CV
    0.47
     affect
    0.47
    Act Density 0.027%

    No Known Activations