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

    Neuronpedia

    INDEX
    Explanations

    preposition + descriptive word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     singularities
    0.50
     otro
    0.47
     lem
    0.47
     menudo
    0.46
     radiant
    0.46
     cest
    0.46
     da
    0.45
    बाट
    0.45
     decadent
    0.45
     telo
    0.45
    POSITIVE LOGITS
    š
    0.44
    ™
    0.44
    ueill
    0.44
     confertim
    0.43
     ಶು
    0.42
    🐟
    0.42
    oomla
    0.42
    💒
    0.41
    สห
    0.40
     ସ
    0.40
    Act Density 0.002%

    No Known Activations