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

    Neuronpedia

    INDEX
    Explanations

    patch

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     μεγαλ
    -0.08
     البعض
    -0.08
    غرب
    -0.08
     πάρ
    -0.08
     abwechslungs
    -0.08
     brauch
    -0.08
    Seit
    -0.08
    ღ
    -0.08
    LOCAL
    -0.08
     المحلي
    -0.08
    POSITIVE LOGITS
     vulnerabilities
    0.09
    漏洞
    0.09
    修
    0.09
    针对
    0.08
     ransomware
    0.08
    安全
    0.08
     corrig
    0.08
     સુધ
    0.08
     segurança
    0.08
     improvements
    0.08
    Act Density 0.007%

    No Known Activations