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

    Neuronpedia

    INDEX
    Explanations

    action or score context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ถุนายน
    0.84
     których
    0.82
     amerikanischen
    0.80
    Meier
    0.79
     hiçbir
    0.79
     Jimenez
    0.79
     mismatched
    0.79
     Grants
    0.78
     Trails
    0.78
     synced
    0.78
    POSITIVE LOGITS
    s
    1.14
    n
    1.06
    r
    0.99
    ন
    0.92
    w
    0.89
    a
    0.86
    ar
    0.86
    to
    0.86
    c
    0.82
    tor
    0.81
    Act Density 0.001%

    No Known Activations