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

    Neuronpedia

    INDEX
    Explanations

    setting game configurations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,$$
    0.45
     midwife
    0.45
     विक्रेता
    0.44
     செய்தார்
    0.44
    istosoma
    0.42
     கோயில்
    0.41
    риз
    0.41
     退
    0.40
     Respiratory
    0.39
     ஊக்கு
    0.39
    POSITIVE LOGITS
    ністю
    0.46
    Cómo
    0.46
    اي
    0.44
    Morgan
    0.43
    юць
    0.41
    យ
    0.41
    Boris
    0.41
    gede
    0.40
    Quand
    0.40
    Vad
    0.40
    Act Density 0.005%

    No Known Activations