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

    Neuronpedia

    INDEX
    Explanations

    ":" followed by true

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     медве
    0.39
    ﺐ
    0.37
     zdoby
    0.36
     housekeeping
    0.34
     shroud
    0.34
    क्रोस
    0.34
    ंकडून
    0.34
    ப்பொரு
    0.33
    ூ
    0.33
     ...");
    0.33
    POSITIVE LOGITS
    false
    0.49
    坵
    0.43
     ignored
    0.43
     false
    0.41
    🚫
    0.40
     kecuali
    0.40
    warning
    0.39
     yanlış
    0.39
    thank
    0.39
    Warning
    0.39
    Act Density 0.001%

    No Known Activations