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

    Neuronpedia

    INDEX
    Explanations

    waterways

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     communism
    -0.07
     mankind
    -0.07
     meals
    -0.07
     parole
    -0.07
    filer
    -0.06
    _quotes
    -0.06
    權
    -0.06
     ['
    -0.06
    War
    -0.06
    (stat
    -0.06
    POSITIVE LOGITS
    $mail
    0.06
    ी।
    0.06
    \/
    0.06
    RUN
    0.06
    `]
    0.06
     audition
    0.06
     pioneer
    0.06
    UIButton
    0.06
    ické
    0.06
    业务
    0.06
    Act Density 0.030%

    No Known Activations