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

    Neuronpedia

    INDEX
    Explanations

    speaking or talking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    topo
    2.75
    ído
    2.44
    ્ઞ
    2.37
     zir
    2.36
    dı
    2.34
    арма
    2.29
     Figur
    2.19
    Etat
    2.18
     tanıt
    2.18
     повідом
    2.16
    POSITIVE LOGITS
    ו
    2.76
    ه
    2.33
    RTC
    2.24
    o
    2.22
     amit
    2.16
    া
    2.15
    z
    2.14
    วิทยา
    2.13
    ل
    2.13
    ল
    2.12
    Act Density 0.774%

    No Known Activations