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

    Neuronpedia

    INDEX
    Explanations

    specific contexts of information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ochi
    0.78
    نين
    0.77
    ining
    0.77
    तात
    0.75
    topping
    0.72
    ples
    0.72
     darunter
    0.71
     असून
    0.71
    pling
    0.71
    adet
    0.70
    POSITIVE LOGITS
     कठिना
    0.86
     CTS
    0.81
    难度
    0.80
     of
    0.79
     reflects
    0.78
     задачу
    0.77
    of
    0.77
     based
    0.77
    Ac
    0.76
     task
    0.76
    Act Density 0.000%

    No Known Activations