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

    Neuronpedia

    INDEX
    Explanations

    Reading guides and reviews

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ับผ
    -0.06
    /mark
    -0.06
    _overlap
    -0.06
     vay
    -0.06
    те
    -0.06
     водой
    -0.06
     Announcement
    -0.06
    _sol
    -0.06
     Packages
    -0.06
     Starting
    -0.06
    POSITIVE LOGITS
    intros
    0.07
    appoint
    0.06
    hum
    0.06
     دوب
    0.06
    attacks
    0.06
    едаг
    0.06
    pcs
    0.06
     Theft
    0.06
     pageNum
    0.06
    _disc
    0.06
    Act Density 0.058%

    No Known Activations