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

    Neuronpedia

    INDEX
    Explanations

    tech

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    RYPT
    -0.08
    文物保护
    -0.08
    ermen
    -0.07
    Ɛ
    -0.07
    值得注意
    -0.07
     yat
    -0.07
     watershed
    -0.07
    opts
    -0.07
     Чер
    -0.07
    UNC
    -0.06
    POSITIVE LOGITS
     mão
    0.07
     Connections
    0.07
     Applying
    0.07
     whereby
    0.07
    "),
↵
    0.07
     mundo
    0.06
    商業
    0.06
     Kyle
    0.06
    iam
    0.06
    뀨
    0.06
    Act Density 0.001%

    No Known Activations