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

    Neuronpedia

    INDEX
    Explanations

    enti

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Reverso
    -0.68
    ging
    -0.67
    gers
    -0.65
    gger
    -0.57
    RefNanny
    -0.57
    Pyx
    -0.55
     Clarke
    -0.55
    tor
    -0.55
    ingi
    -0.54
    ViewImports
    -0.54
    POSITIVE LOGITS
     Efq
    0.97
     myſelf
    0.90
     Theſe
    0.87
     Majefty
    0.85
     Anſ
    0.82
     Reſ
    0.81
     houſe
    0.81
     purpoſe
    0.81
     Cæsar
    0.78
     Houſe
    0.77
    Act Density 0.056%

    No Known Activations