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

    Neuronpedia

    INDEX
    Explanations

    it

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IRE
    -0.07
    mäßig
    -0.07
    icion
    -0.07
    utely
    -0.07
     Với
    -0.07
     reste
    -0.06
    ǔ
    -0.06
     faut
    -0.06
    톧
    -0.06
     adulte
    -0.06
    POSITIVE LOGITS
    (song
    0.07
    /twitter
    0.07
    prob
    0.07
     ,(
    0.07
    xor
    0.07
     ואף
    0.07
    (cb
    0.07
    .comp
    0.07
    traîn
    0.07
    /TR
    0.07
    Act Density 0.002%

    No Known Activations