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

    Neuronpedia

    INDEX
    Explanations

    code block separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ्स
    2.06
    s
    1.91
    ться
    1.66
    ات
    1.36
    ا
    1.32
    ação
    1.30
    ્સ
    1.27
    t
    1.27
     batas
    1.26
    i
    1.25
    POSITIVE LOGITS
     cornerback
    1.19
     ríg
    1.16
    ripción
    1.13
     Bier
    1.09
     northbound
    1.08
     Besonders
    1.08
    з
    1.08
    ிருப்ப
    1.07
     overr
    1.07
    йга
    1.05
    Act Density 0.002%

    No Known Activations