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

    Neuronpedia

    INDEX
    Explanations

    absurdist humor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    V
    0.52
    韋
    0.45
    高
    0.44
     बड़े
    0.44
    Genetic
    0.43
    '+
    0.43
    Стра
    0.43
    بي
    0.42
    Film
    0.42
    遠
    0.42
    POSITIVE LOGITS
     uniformity
    0.53
     superstars
    0.52
    s
    0.52
     mechanisms
    0.50
     کردم
    0.50
     washers
    0.50
     façon
    0.50
    ptive
    0.50
    eers
    0.50
     irradiation
    0.49
    Act Density 0.000%

    No Known Activations