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

    Neuronpedia

    INDEX
    Explanations

    examples and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ianie
    0.54
    BeforeText
    0.51
    んだけど
    0.48
    iatr
    0.47
    뛰
    0.45
    ibis
    0.44
    더
    0.42
    hunger
    0.41
     }:
    0.41
    رفت
    0.40
    POSITIVE LOGITS
     existem
    0.57
     pigs
    0.54
     ámbito
    0.52
     существуют
    0.52
     umana
    0.52
    ட்ச
    0.51
     cynical
    0.51
     thơm
    0.50
     zien
    0.50
     cabo
    0.50
    Act Density 0.002%

    No Known Activations