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

    Neuronpedia

    INDEX
    Explanations

    technical documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ArgsConstructor
    -0.57
    </i>
    -0.55
     mej
    -0.53
    esine
    -0.52
    rena
    -0.52
    chu
    -0.51
    XmlType
    -0.50
    enumi
    -0.50
    ServiceModel
    -0.50
    AxisAlignment
    -0.49
    POSITIVE LOGITS
    <bos>
    1.33
     Jefus
    0.95
     myſelf
    0.94
     itſelf
    0.93
    ſelf
    0.89
     himſelf
    0.88
     themſelves
    0.88
     Majefty
    0.87
     pleaſure
    0.83
    neſs
    0.83
    Act Density 0.014%

    No Known Activations