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

    Neuronpedia

    INDEX
    Explanations

    decoding, deciphering, qualifying

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Dav
    0.52
     Ric
    0.48
     Brah
    0.48
    为其
    0.45
     vremena
    0.45
     merkez
    0.43
     Boh
    0.43
     Auburn
    0.43
     four
    0.43
     Lif
    0.43
    POSITIVE LOGITS
    韌
    0.44
     equivoc
    0.43
    clonal
    0.41
    TypeDef
    0.41
     Decoding
    0.41
    óstico
    0.41
     साग
    0.40
    edra
    0.39
     decipher
    0.39
     Negotiations
    0.38
    Act Density 0.000%

    No Known Activations