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

    Neuronpedia

    INDEX
    Explanations

    sometimes, often, but

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     forthwith
    0.42
    ᱗
    0.38
    FileOutputStream
    0.38
    を用いて
    0.37
     கடும்
    0.37
     огром
    0.37
    abhuto
    0.36
     विशाल
    0.36
     организова
    0.36
    inputSet
    0.36
    POSITIVE LOGITS
     sometimes
    0.58
     parfois
    0.52
     Sometimes
    0.48
     disliked
    0.46
     usually
    0.45
     don
    0.43
     иногда
    0.43
     doesn
    0.42
     manchmal
    0.42
     occasional
    0.41
    Act Density 0.073%

    No Known Activations