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

    Neuronpedia

    INDEX
    Explanations

    towns, locals, teachers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ]")]
    -0.99
     itſelf
    -0.93
    */;
    -0.92
     myſelf
    -0.91
     Jefus
    -0.91
    ^(@)
    -0.90
     Monfieur
    -0.90
     Efq
    -0.88
    MigrationBuilder
    -0.87
     fhort
    -0.86
    POSITIVE LOGITS
    ’
    0.69
     of
    0.63
    '
    0.63
    hips
    0.54
    ,
    0.51
     who
    0.48
     get
    0.47
    Set
    0.46
    受
    0.46
    置
    0.45
    Act Density 1.290%

    No Known Activations