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

    Neuronpedia

    INDEX
    Explanations

    related to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )/\
    0.91
    0.85
    overlay
    0.84
    ►
    0.81
    ி
    0.81
    Truman
    0.79
     tampak
    0.79
    عند
    0.78
    ➢
    0.78
    0.77
    POSITIVE LOGITS
    ar
    0.93
    Појединачна
    0.89
    n
    0.89
    om
    0.84
    aros
    0.84
    р
    0.83
    रूप
    0.80
     odre
    0.79
    LY
    0.79
     apport
    0.78
    Act Density 0.132%

    No Known Activations