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

    Neuronpedia

    INDEX
    Explanations

    specific following words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ümler
    0.46
     MongoClient
    0.44
    ുടെ
    0.42
    <0x8C>
    0.41
    巨大
    0.40
     +#
    0.40
     +\
    0.38
     Plessis
    0.38
    ్ఞ
    0.37
     sauvage
    0.37
    POSITIVE LOGITS
    HV
    0.40
    築
    0.40
    Gob
    0.39
    invalidate
    0.39
     வரைய
    0.39
    Corollary
    0.38
    Theorem
    0.38
    Failed
    0.38
    Rationale
    0.37
    ilyen
    0.37
    Act Density 0.000%

    No Known Activations