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

    Neuronpedia

    INDEX
    Explanations

    Searching or code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iments
    -0.07
     ships
    -0.07
    踏上
    -0.07
    iez
    -0.07
    老兵
    -0.06
    ǃ
    -0.06
     משו
    -0.06
     famine
    -0.06
    .executor
    -0.06
    .timezone
    -0.06
    POSITIVE LOGITS
     ///
    0.08
     PK
    0.07
     <!--
    0.07
    现实中
    0.07
    ");//
    0.07
    <!--
    0.07
     •
    0.07
    Parsed
    0.07
    brid
    0.07
     suppression
    0.07
    Act Density 0.098%

    No Known Activations