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

    Neuronpedia

    INDEX
    Explanations

    say "at"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /.↵↵
    -0.07
    asının
    -0.07
    FLASH
    -0.07
    _date
    -0.06
    (Token
    -0.06
    surface
    -0.06
    CREATE
    -0.06
     Ike
    -0.06
     proprietor
    -0.06
    Prod
    -0.06
    POSITIVE LOGITS
     loosely
    0.07
    ุ้
    0.06
     expanding
    0.06
    \uD
    0.06
    Grab
    0.06
    ोज
    0.06
     защ
    0.06
    //{{
    0.06
     exam
    0.06
    _basis
    0.06
    Act Density 0.011%

    No Known Activations