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

    Neuronpedia

    INDEX
    Explanations

    Prefix

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :\\
    -0.06
    นอ
    -0.06
     обнаруж
    -0.06
     Directions
    -0.06
    mas
    -0.06
    _MEDIA
    -0.06
     feed
    -0.06
    (review
    -0.06
    πισ
    -0.05
    aclass
    -0.05
    POSITIVE LOGITS
    iere
    0.07
    ポート
    0.07
    -com
    0.07
     ====
    0.07
     dude
    0.07
    0.06
     }}↵↵
    0.06
     texte
    0.06
    pent
    0.06
    _program
    0.06
    Act Density 0.003%

    No Known Activations