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

    Neuronpedia

    INDEX
    Explanations

    one

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    지막
    -0.07
     Cand
    -0.07
    舌
    -0.06
    ategies
    -0.06
     яб
    -0.06
     digitally
    -0.06
    Mot
    -0.06
    ilton
    -0.06
    ‌ب
    -0.06
    =my
    -0.06
    POSITIVE LOGITS
     Nou
    0.07
    etzt
    0.07
    045
    0.06
    ..↵
    0.06
    uming
    0.06
     demi
    0.06
    conto
    0.06
     cabo
    0.06
     фай
    0.06
    .rate
    0.06
    Act Density 0.000%

    No Known Activations