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

    Neuronpedia

    INDEX
    Explanations

    build-essential software packaging

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Euch
    0.38
    matches
    0.37
     berse
    0.37
    touches
    0.37
     Apache
    0.36
    kie
    0.36
    -'
    0.36
    forcement
    0.35
    0.35
    Apache
    0.35
    POSITIVE LOGITS
     sourced
    0.48
    সূত্র
    0.44
     accumulating
    0.44
    TestSource
    0.43
    рби
    0.40
    sourceEncoding
    0.39
    乚
    0.39
     intellectual
    0.39
    소스
    0.39
     supplemented
    0.38
    Act Density 0.000%

    No Known Activations