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

    Neuronpedia

    INDEX
    Explanations

    transition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Keynes
    -0.07
     Mush
    -0.07
     Fork
    -0.06
     Canton
    -0.06
     فلس
    -0.06
    _AUX
    -0.06
     rasp
    -0.06
     watering
    -0.06
     волод
    -0.06
     KY
    -0.06
    POSITIVE LOGITS
     premiere
    0.07
    (meta
    0.07
    -------------
    0.07
     kişilerin
    0.07
    ние
    0.06
     exclude
    0.06
     temporal
    0.06
     triggered
    0.06
    一下
    0.06
    (IC
    0.06
    Act Density 0.001%

    No Known Activations