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

    Neuronpedia

    INDEX
    Explanations

    data analysis, science, and privacy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    รู้จัก
    0.44
    development
    0.39
    리티
    0.39
    ો
    0.37
    意见
    0.36
    లా
    0.35
    發展
    0.35
    評價
    0.34
     lightweight
    0.34
    இய
    0.34
    POSITIVE LOGITS
    बेस
    0.68
     osobow
    0.64
    सेट
    0.63
     sets
    0.61
    flow
    0.61
    verse
    0.60
    sets
    0.60
     breach
    0.60
    flows
    0.59
     analytics
    0.59
    Act Density 0.157%

    No Known Activations