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

    Neuronpedia

    INDEX
    Explanations

    games

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [f
    -0.07
    (calendar
    -0.07
    .simple
    -0.06
    .GONE
    -0.06
    _arc
    -0.06
    Amazing
    -0.06
    ピー
    -0.06
    .Field
    -0.06
    	fs
    -0.06
     isAuthenticated
    -0.06
    POSITIVE LOGITS
    ��
    0.07
    )set
    0.07
    ̃
    0.07
     trưng
    0.06
    مول
    0.06
     Ethiopia
    0.06
    ICLE
    0.06
     तम
    0.06
    BS
    0.06
    -vous
    0.06
    Act Density 0.010%

    No Known Activations