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

    Neuronpedia

    INDEX
    Explanations

    ar

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kob
    -0.07
     Sleep
    -0.06
     Powder
    -0.06
     Mug
    -0.06
     COLUMN
    -0.06
    obile
    -0.06
     complexity
    -0.06
     compel
    -0.06
    _micro
    -0.06
     victims
    -0.06
    POSITIVE LOGITS
    월까지
    0.06
    ;↵↵↵↵↵
    0.06
    ABILITY
    0.06
    .Direction
    0.06
    estado
    0.06
    -object
    0.06
    <uint
    0.06
     consequently
    0.06
    停
    0.06
     кат
    0.06
    Act Density 0.001%

    No Known Activations