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

    Neuronpedia

    INDEX
    Explanations

    say "the ending -ize"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Schema
    -0.07
     mContext
    -0.07
     bread
    -0.06
    section
    -0.06
     discharge
    -0.06
     isIn
    -0.06
     мов
    -0.06
     Všech
    -0.06
     xmlDoc
    -0.06
     '''
↵
    -0.06
    POSITIVE LOGITS
     �
    0.06
     almost
    0.06
     ）
    0.06
    !]
    0.06
     nx
    0.06
    allah
    0.06
    'à
    0.06
     تخصص
    0.06
    .PLL
    0.06
     secretly
    0.06
    Act Density 0.004%

    No Known Activations