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

    Neuronpedia

    INDEX
    Explanations

    Python code or errors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ํา
    0.40
     émotion
    0.37
    라는
    0.36
    isiaj
    0.35
    Ъ
    0.34
     eigens
    0.34
     argentinos
    0.34
    北美
    0.34
    ILIO
    0.33
    PARTMENT
    0.33
    POSITIVE LOGITS
     Keep
    0.41
    etc
    0.40
     Cultures
    0.39
    icing
    0.39
    <0x0D>
    0.39
     Reform
    0.37
    other
    0.37
     Other
    0.37
    f
    0.37
     Guarantee
    0.36
    Act Density 0.001%

    No Known Activations