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

    Neuronpedia

    INDEX
    Explanations

    atoon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    影響
    -0.07
    <Renderer
    -0.07
     ат
    -0.07
    irus
    -0.06
    _OP
    -0.06
     correo
    -0.06
     total
    -0.06
     Kaz
    -0.06
     millionaire
    -0.06
     mirror
    -0.06
    POSITIVE LOGITS
    Indent
    0.06
     gab
    0.06
    ्तन
    0.06
    ga
    0.06
     Although
    0.06
    gal
    0.06
    _contract
    0.06
     According
    0.06
    .steps
    0.06
    \admin
    0.06
    Act Density 0.000%

    No Known Activations