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

    Neuronpedia

    INDEX
    Explanations

    markdown table headers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Voici
    0.43
    Base
    0.40
    Empty
    0.40
    Für
    0.39
    如下图
    0.39
     segreg
    0.39
    Guidelines
    0.38
     Leute
    0.38
    ក្នុងការ
    0.37
    ்த்து
    0.37
    POSITIVE LOGITS
    YN
    0.40
     sni
    0.38
     volante
    0.37
     dźwię
    0.37
    낯
    0.36
     المن
    0.36
     spieg
    0.36
     columna
    0.36
     cipher
    0.36
     breaches
    0.36
    Act Density 0.042%

    No Known Activations