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

    Neuronpedia

    INDEX
    Explanations

    [

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Reviews
    -0.08
    elin
    -0.08
    .Members
    -0.08
    dess
    -0.07
    ）、
    -0.07
    _led
    -0.07
    赢得
    -0.07
    üns
    -0.07
    <Location
    -0.07
    resume
    -0.07
    POSITIVE LOGITS
    メディア
    0.07
     السلطات
    0.07
     modalità
    0.07
     применя
    0.07
     theor
    0.07
    (quantity
    0.07
     `,
    0.07
    ->↵
    0.07
     organizational
    0.06
    ത
    0.06
    Act Density 0.012%

    No Known Activations