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

    Neuronpedia

    INDEX
    Explanations

    before or while

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    が高い
    0.95
    مار
    0.93
    كل
    0.92
     대해서
    0.91
     basicamente
    0.91
     ámbitos
    0.90
    𝓛
    0.89
     или
    0.87
     aquell
    0.87
    が存在
    0.86
    POSITIVE LOGITS
    ip
    0.98
    ur
    0.90
    are
    0.90
    ி
    0.90
    essä
    0.89
    änt
    0.89
    ಧಾರವಾಡ
    0.89
    at
    0.88
    ik
    0.88
    artney
    0.88
    Act Density 0.036%

    No Known Activations