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

    Neuronpedia

    INDEX
    Explanations

    weaknesses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    げる
    0.39
    ヴィ
    0.38
    лям
    0.37
    ࿔
    0.37
    idey
    0.36
    isieren
    0.36
     shoved
    0.36
    resso
    0.36
    ждая
    0.36
    acylglycer
    0.36
    POSITIVE LOGITS
    0.41
     non
    0.41
     Gulf
    0.40
     details
    0.40
     detailed
    0.37
     Non
    0.37
     juridique
    0.37
     February
    0.36
     compliance
    0.36
     US
    0.35
    Act Density 0.000%

    No Known Activations