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

    Neuronpedia

    INDEX
    Explanations

    introducing questions or topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    簡單
    0.45
    ١
    0.41
    لسل
    0.40
    ленность
    0.40
     crumbling
    0.40
     obtuse
    0.40
     truc
    0.40
     Після
    0.39
    જી
    0.39
     muebles
    0.39
    POSITIVE LOGITS
    ⓡ
    0.50
    ációs
    0.46
    사와
    0.46
     assess
    0.46
     appell
    0.45
     pedibus
    0.45
    üse
    0.44
    스와
    0.44
     and
    0.44
     مقام
    0.43
    Act Density 0.001%

    No Known Activations