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

    Neuronpedia

    INDEX
    Explanations

    primarily recognized

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     অথবা
    1.05
    తో
    1.00
    мето
    1.00
    czą
    0.99
    пор
    0.97
    費用
    0.95
     rhet
    0.95
    gı
    0.92
    pi
    0.92
     کف
    0.92
    POSITIVE LOGITS
     minimization
    0.96
     statistical
    0.95
    oplankton
    0.93
     CNN
    0.93
    Cindy
    0.92
    [["
    0.90
     minimizing
    0.90
    JSONObject
    0.90
    ️
    0.90
     jitter
    0.89
    Act Density 0.000%

    No Known Activations