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

    Neuronpedia

    INDEX
    Explanations

    foreign languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    できる
    0.64
    SpecID
    0.64
     solltest
    0.62
     لیں
    0.59
     timelapse
    0.58
    FUNC
    0.57
    ूज
    0.56
     specif
    0.55
     italics
    0.55
     Bhav
    0.54
    POSITIVE LOGITS
    icano
    0.64
    ísimo
    0.56
     чувство
    0.55
    čení
    0.54
    gesellschaft
    0.52
    做事
    0.51
    ina
    0.51
     người
    0.50
    比如說
    0.50
    gebäude
    0.50
    Act Density 0.023%

    No Known Activations