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

    Neuronpedia

    INDEX
    Explanations

    pretends

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     अकेले
    0.47
    ڳ
    0.46
     úpl
    0.45
    無線
    0.45
    ELINE
    0.44
    etí
    0.42
    кість
    0.41
    ées
    0.41
    мок
    0.41
    ギター
    0.41
    POSITIVE LOGITS
    కాలు
    0.44
     releg
    0.43
     sabot
    0.43
     demol
    0.42
     dissip
    0.42
     have
    0.41
     değer
    0.41
     investimento
    0.41
     mitochondrial
    0.41
     invers
    0.40
    Act Density 0.001%

    No Known Activations