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

    Neuronpedia

    INDEX
    Explanations

    personal narratives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     My
    -0.92
    ,
    -0.90
     
    -0.86
     Can
    -0.81
     I
    -0.77
     U
    -0.76
     (
    -0.72
     B
    -0.70
    .
    -0.70
     P
    -0.69
    POSITIVE LOGITS
     Efq
    1.51
     فريبيس
    1.40
     Theſe
    1.40
     Monfieur
    1.40
     Anſ
    1.37
    expandindo
    1.36
     ་་
    1.35
     ―――――
    1.35
     Reſ
    1.35
     Majefty
    1.33
    Act Density 1.735%

    No Known Activations