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

    Neuronpedia

    INDEX
    Explanations

    n followed by comma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ('')
    0.43
    Kya
    0.41
    шты
    0.39
    "`
    0.39
    кер
    0.38
     bolognese
    0.36
    Declar
    0.36
     embedded
    0.35
    accord
    0.35
     few
    0.35
    POSITIVE LOGITS
    ีด
    0.44
    ഴിലാ
    0.41
     AREA
    0.40
    髦
    0.36
    ্যাশ
    0.36
    žila
    0.36
     Repe
    0.36
    ;%(
    0.36
     በፊት
    0.35
    LINE
    0.35
    Act Density 0.006%

    No Known Activations