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

    Neuronpedia

    INDEX
    Explanations

    key moments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     logarithm
    0.54
    Ordenar
    0.51
     multiplying
    0.49
     malleable
    0.46
     logarithmic
    0.46
     விருப்ப
    0.46
     করিতেছে
    0.46
    占用
    0.45
    𒋫
    0.45
     solubility
    0.44
    POSITIVE LOGITS
     highlights
    0.84
    highlights
    0.83
     Highlights
    0.77
    Highlights
    0.66
     overall
    0.63
     Overall
    0.63
     المباراة
    0.62
     commentary
    0.62
     despite
    0.61
    Overall
    0.61
    Act Density 0.003%

    No Known Activations