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

    Neuronpedia

    INDEX
    Explanations

    Morality/ethics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    酢
    -0.08
    .selection
    -0.07
    筦
    -0.07
     reportedly
    -0.07
     geçen
    -0.07
    .goods
    -0.07
     Украин
    -0.07
    SENSOR
    -0.07
    /index
    -0.07
     merchandise
    -0.07
    POSITIVE LOGITS
    IME
    0.08
    band
    0.08
    옿
    0.07
    疲
    0.07
    ided
    0.07
    حكيم
    0.07
    oteca
    0.07
    cale
    0.07
    prit
    0.07
     Pixels
    0.07
    Act Density 0.081%

    No Known Activations