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

    Neuronpedia

    INDEX
    Explanations

    beyond all

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kalın
    0.58
    itat
    0.57
    ètement
    0.57
    anns
    0.57
    oric
    0.55
     ܗ
    0.55
     cultivés
    0.55
     tumeur
    0.54
    čili
    0.53
     Omphalodes
    0.53
    POSITIVE LOGITS
     lower
    0.50
    各
    0.46
    える
    0.45
    ל
    0.44
    以下
    0.44
    다
    0.44
    마
    0.43
     lighter
    0.43
    им
    0.43
    어
    0.41
    Act Density 0.000%

    No Known Activations