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

    Neuronpedia

    INDEX
    Explanations

    lack, limitation, restriction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     quantities
    0.46
     póź
    0.44
     somewhat
    0.41
    a
    0.41
     smooth
    0.40
     සැ
    0.40
    0
    0.40
    自身的
    0.39
     symbolize
    0.39
    some
    0.39
    POSITIVE LOGITS
     utbild
    0.49
     alá
    0.47
     eftersom
    0.45
     creando
    0.44
     університе
    0.44
    ，”
    0.44
     !!,
    0.43
    㳳
    0.43
     осві
    0.43
    ভ্র
    0.43
    Act Density 0.004%

    No Known Activations