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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Payment
    -0.06
     Hak
    -0.06
     мин
    -0.06
     mpz
    -0.06
    _by
    -0.06
     外部リンク
    -0.06
     Fare
    -0.05
     经
    -0.05
     dài
    -0.05
     pořad
    -0.05
    POSITIVE LOGITS
     initiate
    0.07
    etal
    0.07
     Darth
    0.06
    [length
    0.06
     seçim
    0.06
     CHECK
    0.06
     weapon
    0.06
     gül
    0.06
    uppet
    0.06
     narc
    0.06
    Act Density 0.000%

    No Known Activations