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

    Neuronpedia

    INDEX
    Explanations

    Negation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    怎么办
    -0.09
    genre
    -0.08
    ​របស់
    -0.08
    ​យ
    -0.08
     како
    -0.08
    ucz
    -0.08
     البيان
    -0.08
    យ
    -0.07
    uum
    -0.07
     gastronom
    -0.07
    POSITIVE LOGITS
     hassles
    0.10
     hassle
    0.10
     undue
    0.10
    ാതെ
    0.09
    Duplicates
    0.09
     fuss
    0.09
    忘初心
    0.09
     surprises
    0.09
     distractions
    0.09
     лиш
    0.09
    Act Density 0.290%

    No Known Activations