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

    Neuronpedia

    INDEX
    Explanations

    Common English articles/prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ursion
    -0.07
    ใหญ
    -0.06
     SAL
    -0.06
    ipient
    -0.06
    لام
    -0.06
     Mathematic
    -0.06
     personne
    -0.06
    君
    -0.06
    바
    -0.06
     Welt
    -0.06
    POSITIVE LOGITS
    BackgroundColor
    0.07
    ff
    0.07
     Challenger
    0.07
    _al
    0.06
    essage
    0.06
    <Renderer
    0.06
    	up
    0.06
    (entry
    0.06
    (previous
    0.06
     financially
    0.06
    Act Density 0.006%

    No Known Activations