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

    Neuronpedia

    INDEX
    Explanations

    specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    成
    0.44
    akannya
    0.43
    Lea
    0.42
    ього
    0.41
    ugi
    0.40
    getLong
    0.40
    opio
    0.40
    Jan
    0.40
     araw
    0.39
    가능
    0.38
    POSITIVE LOGITS
     imasmim
    0.52
     atop
    0.46
     counterbalance
    0.45
     tribute
    0.42
     patitth
    0.41
     hinzuf
    0.41
    唖
    0.41
     இருக்கிறார்
    0.41
     शिर
    0.41
     बहाल
    0.40
    Act Density 0.000%

    No Known Activations