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

    Neuronpedia

    INDEX
    Explanations

    superhero

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Compute
    -0.07
    ¾
    -0.06
     Reminder
    -0.06
     Highly
    -0.06
    -Cds
    -0.06
     radius
    -0.06
     bee
    -0.06
     victorious
    -0.06
    .steps
    -0.06
     Mechanical
    -0.06
    POSITIVE LOGITS
    uí
    0.07
     CALC
    0.06
    repair
    0.06
     двиг
    0.06
    utenant
    0.06
    oping
    0.06
    ycling
    0.06
    Originally
    0.06
     ماسه
    0.06
     корп
    0.06
    Act Density 0.019%

    No Known Activations