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

    Neuronpedia

    INDEX
    Explanations

    mathematical fractions format

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bidding
    1.05
    whitespace
    1.00
    enhancing
    0.99
     /(
    0.99
    ు
    0.98
     对于
    0.98
     dividing
    0.97
    यु
    0.96
    ذة
    0.93
     aversion
    0.91
    POSITIVE LOGITS
    ר
    1.47
    {}{
    1.47
    er
    1.39
    торой
    1.31
    ilihan
    1.31
    ības
    1.19
    তবু
    1.18
    ер
    1.15
     voltar
    1.14
     volver
    1.13
    Act Density 0.020%

    No Known Activations