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

    Neuronpedia

    INDEX
    Explanations

    way

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     DOJ
    -0.06
    ");↵↵↵
    -0.06
    //'
    -0.06
    badge
    -0.06
    Configuration
    -0.06
    Năm
    -0.06
     compañ
    -0.06
     Kra
    -0.06
    ake
    -0.06
    Ingredient
    -0.06
    POSITIVE LOGITS
    .qq
    0.07
    ılıp
    0.07
    ือ
    0.07
    .visible
    0.06
    .graphics
    0.06
    址
    0.06
    .factor
    0.06
    °F
    0.06
     дорож
    0.06
    .unique
    0.06
    Act Density 0.026%

    No Known Activations