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

    Neuronpedia

    INDEX
    Explanations

    if

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    シ
    -0.07
    .Monad
    -0.07
    Deleting
    -0.07
     Papa
    -0.06
     Sapphire
    -0.06
     كنت
    -0.06
     Opera
    -0.06
     Кар
    -0.06
    fat
    -0.06
     цер
    -0.06
    POSITIVE LOGITS
     neut
    0.07
    imshow
    0.07
    (created
    0.07
    _row
    0.07
    _flight
    0.06
     row
    0.06
     hei
    0.06
     newPosition
    0.06
    lide
    0.06
     stm
    0.06
    Act Density 0.039%

    No Known Activations