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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _MA
    -0.07
    career
    -0.07
     duplicate
    -0.07
    mart
    -0.07
     stadiums
    -0.07
    (alias
    -0.06
     Iranian
    -0.06
    全
    -0.06
     Marks
    -0.06
     pořad
    -0.06
    POSITIVE LOGITS
     DateTimeOffset
    0.06
     proletariat
    0.06
     ElementRef
    0.06
    .bpm
    0.06
    unto
    0.06
    bose
    0.06
    ]<=
    0.05
     Affero
    0.05
     Бі
    0.05
     Compiled
    0.05
    Act Density 0.003%

    No Known Activations