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

    Neuronpedia

    INDEX
    Explanations

    kel followed by specific suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ailles
    0.39
    ungsl
    0.39
     боя
    0.38
    とう
    0.37
     save
    0.37
     победи
    0.36
    ident
    0.36
     discovering
    0.36
    ᱗
    0.36
     प्रार्थ
    0.36
    POSITIVE LOGITS
     kel
    0.55
    Kel
    0.52
    idoscope
    0.50
     Kel
    0.46
    켈
    0.41
    kel
    0.38
     ગયો
    0.38
    ompok
    0.37
    KEL
    0.37
     sensory
    0.36
    Act Density 0.003%

    No Known Activations