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
     Season
    -0.07
     роботу
    -0.07
     Gratis
    -0.06
     Hunger
    -0.06
     sont
    -0.06
    д
    -0.06
     Evet
    -0.06
     ISP
    -0.06
    �
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    كوم
    0.07
     RESP
    0.07
    `.↵
    0.07
    .style
    0.07
    (QStringLiteral
    0.07
     mấy
    0.06
    �
    0.06
     nationwide
    0.06
    what
    0.06
    plers
    0.06
    Act Density 0.000%

    No Known Activations