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

    Neuronpedia

    INDEX
    Explanations

    internet chat logs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     norm
    -0.06
    141
    -0.06
    legate
    -0.06
    _bot
    -0.06
     Clarence
    -0.06
    577
    -0.06
    xr
    -0.06
    P
    -0.06
    on
    -0.06
    Reservation
    -0.06
    POSITIVE LOGITS
    emek
    0.07
    (Pointer
    0.07
    (inner
    0.06
    OutOfRangeException
    0.06
     childhood
    0.06
    (board
    0.06
     эк
    0.06
     generado
    0.06
    .art
    0.06
    -Semit
    0.06
    Act Density 0.026%

    No Known Activations