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

    Neuronpedia

    INDEX
    Explanations

    movies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     weltweit
    -0.08
     cle
    -0.07
     volunteered
    -0.07
     cleared
    -0.07
    复
    -0.07
     alloys
    -0.07
     unofficial
    -0.07
    イ
    -0.07
    cle
    -0.07
    _repr
    -0.07
    POSITIVE LOGITS
     Waiting
    0.10
     rustig
    0.10
     dwelling
    0.09
     прогул
    0.09
     постеп
    0.09
     contempl
    0.09
     Konzentr
    0.09
     langzaam
    0.09
     केन्द्र
    0.09
     протяжении
    0.09
    Act Density 0.040%

    No Known Activations