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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and connectors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    there
    1.23
     terribly
    1.22
     silvest
    1.17
     seems
    1.16
     sneaky
    1.16
     тебя
    1.10
     faintly
    1.10
     haunts
    1.10
     instar
    1.10
     There
    1.09
    POSITIVE LOGITS
     and
    1.34
    และการ
    1.18
    ف
    1.10
    ציה
    1.09
    และความ
    1.06
    Ти
    1.05
    そして
    1.04
    और
    1.04
     և
    1.02
     💪
    1.01
    Act Density 0.585%

    No Known Activations