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

    Neuronpedia

    INDEX
    Explanations

    middle

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Houſe
    -0.82
     itſelf
    -0.82
     myſelf
    -0.81
     photolibrary
    -0.80
     Efq
    -0.78
     Reſ
    -0.77
     Theſe
    -0.75
     Anſ
    -0.75
    ValueStyle
    -0.71
     Majefty
    -0.71
    POSITIVE LOGITS
     or
    0.54
     argc
    0.52
    c
    0.49
    ,
    0.49
    w
    0.49
    mers
    0.47
    хьтан
    0.47
    /
    0.47
     (
    0.46
     C
    0.45
    Act Density 0.026%

    No Known Activations