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

    Neuronpedia

    INDEX
    Explanations

    dynam

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rough
    -0.08
     LSD
    -0.07
    .rl
    -0.07
    ріб
    -0.06
    หาก
    -0.06
    _BC
    -0.06
     voiced
    -0.06
    orary
    -0.06
     Dublin
    -0.06
    Ошибка
    -0.06
    POSITIVE LOGITS
    -------
    0.07
    expire
    0.07
    ไม
    0.07
    (animated
    0.06
    ρυ
    0.06
    109
    0.06
     Gig
    0.06
    unded
    0.06
     mümkün
    0.06
    ви
    0.06
    Act Density 0.007%

    No Known Activations