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

    Neuronpedia

    INDEX
    Explanations

    keywords for technical/formal topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    禳
    0.50
     yoki
    0.46
    dogan
    0.45
    സ്ഥ
    0.45
    ないので
    0.44
    ică
    0.44
     কিংবা
    0.43
    或其他
    0.42
    کو
    0.42
    と思われる
    0.42
    POSITIVE LOGITS
     jednu
    0.47
     구분
    0.46
     jednom
    0.45
     люблю
    0.44
     niacin
    0.44
     avid
    0.44
     其中
    0.43
     പങ്കെടു
    0.43
    เยอะ
    0.43
     MeOH
    0.42
    Act Density 0.005%

    No Known Activations