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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sacram
    -0.07
     материал
    -0.07
     bureaucracy
    -0.07
     '((
    -0.07
    Failure
    -0.06
     представляет
    -0.06
     '"
    -0.06
     corrupt
    -0.06
    selector
    -0.06
    alert
    -0.06
    POSITIVE LOGITS
     indispens
    0.07
     اندازه
    0.06
    �
    0.06
     explosives
    0.06
    (),↵
    0.06
    .Calendar
    0.06
    Transition
    0.06
     Clarence
    0.06
     renowned
    0.06
    _ray
    0.06
    Act Density 0.000%

    No Known Activations