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

    Neuronpedia

    INDEX
    Explanations

    chemical reactions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _within
    -0.07
    ielding
    -0.07
     corrupt
    -0.07
     imu
    -0.06
     murderous
    -0.06
     Armen
    -0.06
    .Return
    -0.06
    _medium
    -0.06
    еса
    -0.06
     dumb
    -0.06
    POSITIVE LOGITS
     intersections
    0.07
     deficiency
    0.07
     پي
    0.06
     ActionTypes
    0.06
     resin
    0.06
     voiture
    0.06
    -generator
    0.06
    _fsm
    0.06
    пп
    0.06
     Plex
    0.06
    Act Density 0.019%

    No Known Activations