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

    Neuronpedia

    INDEX
    Explanations

    password

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    яти
    -0.07
    _cleanup
    -0.07
     Governor
    -0.07
    _ORIGIN
    -0.07
    赫
    -0.06
    زية
    -0.06
     chắc
    -0.06
    ्रदर
    -0.06
    ุต
    -0.06
     Wells
    -0.06
    POSITIVE LOGITS
     編
    0.07
    [top
    0.06
    yntax
    0.06
    _linked
    0.06
    textbox
    0.06
    冒
    0.06
    taken
    0.06
    .vec
    0.06
    ersen
    0.06
    <Rigidbody
    0.06
    Act Density 0.007%

    No Known Activations