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

    Neuronpedia

    INDEX
    Explanations

    Repetitive or nonsensical text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Trip
    -0.09
     WAY
    -0.08
     Arrangement
    -0.08
    -prof
    -0.08
     emf
    -0.07
     arranc
    -0.07
    äub
    -0.07
     Tourism
    -0.07
    Trip
    -0.07
    Arrangement
    -0.07
    POSITIVE LOGITS
    还有
    0.08
    关于
    0.08
     επιλογ
    0.08
     مواجهة
    0.08
    失
    0.08
    Bul
    0.08
    Malformed
    0.08
    任
    0.07
    μένες
    0.07
    voli
    0.07
    Act Density 0.012%

    No Known Activations