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

    Neuronpedia

    INDEX
    Explanations

    code and data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     egt
    -0.08
    估
    -0.07
     admitting
    -0.07
    Hola
    -0.06
     ustanov
    -0.06
     pathogens
    -0.06
     acclaim
    -0.06
     meds
    -0.06
     billeder
    -0.06
     힘
    -0.06
    POSITIVE LOGITS
    subscriber
    0.07
    //------------------------------------------------------------------------------↵↵
    0.07
    SECTION
    0.07
    adero
    0.07
    ESP
    0.06
    منت
    0.06
    isecond
    0.06
    TextBoxColumn
    0.06
    γού
    0.06
    -direction
    0.06
    Act Density 8.472%

    No Known Activations