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

    Neuronpedia

    INDEX
    Explanations

    @

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     shared
    -0.08
     ngừng
    -0.07
    Ether
    -0.07
     repos
    -0.06
     Phú
    -0.06
     NR
    -0.06
     orbits
    -0.06
     Бор
    -0.06
    -count
    -0.06
     Πολ
    -0.06
    POSITIVE LOGITS
     whatsoever
    0.07
    Bron
    0.06
    Checkbox
    0.06
     Backup
    0.06
     ked
    0.06
    �
    0.06
    हम
    0.06
    승
    0.06
     приготовить
    0.06
    Descending
    0.06
    Act Density 0.007%

    No Known Activations