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

    Neuronpedia

    INDEX
    Explanations

    directly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _est
    -0.06
     pož
    -0.06
    +-+-+-+-
    -0.06
     ta
    -0.06
    (_.
    -0.06
    ПО
    -0.06
    لمات
    -0.06
    essa
    -0.06
     '*.
    -0.06
     кисл
    -0.06
    POSITIVE LOGITS
    right
    0.08
    >")↵
    0.07
    росто
    0.07
     Meditation
    0.07
     simple
    0.07
    ρωπα
    0.07
     district
    0.07
    řízení
    0.06
     直
    0.06
    global
    0.06
    Act Density 0.009%

    No Known Activations