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

    Neuronpedia

    INDEX
    Explanations

    clear

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    $↵
    -0.06
    ึกษ
    -0.06
     Musical
    -0.06
     alıyor
    -0.06
    veedor
    -0.06
     timedelta
    -0.06
    `);↵
    -0.06
     Respect
    -0.06
    ========↵
    -0.06
    _rl
    -0.06
    POSITIVE LOGITS
    _opts
    0.07
     мені
    0.07
     giants
    0.07
    fsp
    0.07
     slag
    0.07
    atted
    0.06
     drains
    0.06
     اینجا
    0.06
    <User
    0.06
     Lars
    0.06
    Act Density 0.011%

    No Known Activations