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

    Neuronpedia

    INDEX
    Explanations

    model widely

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     S
    0.46
     Ս
    0.41
    𝗦
    0.38
    lnk
    0.38
     الس
    0.37
     বাহ
    0.37
     लिया
    0.36
    льник
    0.36
    شناسی
    0.36
    𝟰
    0.35
    POSITIVE LOGITS
    Em
    0.46
     Em
    0.40
     Dutt
    0.35
    Art
    0.35
     em
    0.35
     Emm
    0.34
    éma
    0.34
    -
    0.34
    /
    0.34
    Wei
    0.33
    Act Density 0.015%

    No Known Activations