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

    Neuronpedia

    INDEX
    Explanations

    invasion of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unenforceable
    1.87
     fleeting
    1.68
     chimney
    1.67
     flexibility
    1.66
    是因為
    1.63
     extinguisher
    1.63
     menstrual
    1.61
     homicide
    1.60
     crowning
    1.59
     chemokine
    1.59
    POSITIVE LOGITS
    อ
    2.38
    i
    2.34
    に
    2.23
    с
    2.20
    ه
    2.17
    or
    2.06
    에
    2.06
    and
    2.05
    ut
    1.97
    א
    1.97
    Act Density 0.007%

    No Known Activations