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

    Neuronpedia

    INDEX
    Explanations

    conditional logic and comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bool
    0.78
    also
    0.76
    d
    0.72
    windows
    0.71
    try
    0.71
    within
    0.71
    您
    0.68
    得分
    0.67
     आणखी
    0.67
     ഒരു
    0.67
    POSITIVE LOGITS
     differenza
    0.90
     différence
    0.88
     rakyat
    0.84
     dissimilar
    0.77
     identidad
    0.76
     unordered
    0.75
     disputa
    0.75
     comparação
    0.73
     trampled
    0.73
     privada
    0.73
    Act Density 0.042%

    No Known Activations