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

    Neuronpedia

    INDEX
    Explanations

    java code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Za
    0.40
    Learning
    0.39
    Esp
    0.39
    يبقى
    0.39
    Organizations
    0.37
    ZA
    0.37
     הה
    0.36
    Either
    0.36
    Has
    0.36
    Mapa
    0.36
    POSITIVE LOGITS
    ake
    0.40
    oured
    0.38
    义务
    0.38
     Forced
    0.38
    xel
    0.38
    inson
    0.37
    otum
    0.37
     Dyke
    0.36
     ಇದೆ
    0.36
    磨
    0.36
    Act Density 0.003%

    No Known Activations