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

    Neuronpedia

    INDEX
    Explanations

    remember

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ỏ
    -0.07
    (ExpectedConditions
    -0.06
    ümüş
    -0.06
    .localtime
    -0.06
     inverted
    -0.06
     aio
    -0.06
    仮
    -0.06
     rodi
    -0.06
     nowrap
    -0.06
    ดำ
    -0.06
    POSITIVE LOGITS
     setAddress
    0.07
    FLICT
    0.07
     میکن
    0.07
    onald
    0.07
    ,D
    0.06
    .Weight
    0.06
    colm
    0.06
    ammers
    0.06
     victims
    0.06
    bers
    0.06
    Act Density 0.010%

    No Known Activations