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

    Neuronpedia

    INDEX
    Explanations

    breakdown explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lawfully
    0.64
    遭受
    0.61
     unlawfully
    0.60
     intolerable
    0.60
    ിക്കുകയും
    0.58
     Необходимо
    0.57
    从未
    0.57
     Subsequently
    0.57
     abhor
    0.57
    ニュアル
    0.57
    POSITIVE LOGITS
     थोड़ा
    1.06
     trochu
    1.04
     tweaks
    1.03
    ちょっと
    1.00
     tweaked
    0.96
     немного
    0.96
     trochę
    0.95
     একটু
    0.95
     lidt
    0.94
     nerdy
    0.93
    Act Density 2.774%

    No Known Activations