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

    Neuronpedia

    INDEX
    Explanations

    to everyone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     erstwhile
    0.42
     goodies
    0.42
     fanno
    0.41
    च्चय
    0.39
     incremento
    0.39
     essendo
    0.38
     maniera
    0.38
     নিতান্ত
    0.38
     अनिवार
    0.38
     BEING
    0.37
    POSITIVE LOGITS
    制造商
    0.31
     swiss
    0.30
    "
    0.30
     decoration
    0.30
    ब्र
    0.29
    aia
    0.29
    时间和
    0.29
    屏幕
    0.28
    优雅
    0.28
    aporation
    0.28
    Act Density 0.000%

    No Known Activations