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

    Neuronpedia

    INDEX
    Explanations

    grep implementation instruction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    snippets
    0.44
     semi
    0.37
    🔦
    0.37
     முன்ன
    0.36
    連携
    0.36
     seamless
    0.35
    瞬间
    0.35
     thể
    0.34
    RCB
    0.34
    gulation
    0.34
    POSITIVE LOGITS
    profits
    0.43
    比如说
    0.42
    比如說
    0.42
    例如
    0.42
     Sauer
    0.41
     K
    0.41
     GAO
    0.40
     मसलन
    0.40
    丵
    0.40
    េស
    0.40
    Act Density 0.002%

    No Known Activations