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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hetically
    -1.14
    ⓧ
    -0.70
     nakalista
    -0.69
    RetentionPolicy
    -0.67
    featureID
    -0.66
     Normdatei
    -0.65
     AssemblyTitle
    -0.63
    ScopeManager
    -0.61
    ISupport
    -0.60
    providedIn
    -0.60
    POSITIVE LOGITS
     /\.
    0.52
    尔斯
    0.52
    XmlEnum
    0.52
    nitzer
    0.49
     Faker
    0.48
     Januari
    0.48
     sẻ
    0.47
     stage
    0.47
    ̷
    0.47
     pelle
    0.46
    Act Density 1.723%

    No Known Activations