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

    Neuronpedia

    INDEX
    Explanations

    operating system details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    itu
    0.38
     piuttosto
    0.37
    मील
    0.37
     Rather
    0.36
     rather
    0.35
     iar
    0.34
    陆章
    0.33
     allemand
    0.33
    itim
    0.33
     chứ
    0.33
    POSITIVE LOGITS
     עם
    0.42
    WITH
    0.40
     باستخدام
    0.37
    With
    0.37
    하거나
    0.37
     WITH
    0.36
     albeit
    0.35
    vgili
    0.35
    ,
    0.35
    웰
    0.35
    Act Density 0.156%

    No Known Activations