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

    Neuronpedia

    INDEX
    Explanations

    references to complexity or sophistication in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    complex logic and workflows

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    windowFixed
    -0.66
    MLLoader
    -0.65
    migrationBuilder
    -0.64
    Rptr
    -0.58
    findpost
    -0.56
    skjaer
    -0.55
     Ringo
    -0.54
     Paglinawan
    -0.53
    ########.
    -0.52
    providedIn
    -0.52
    POSITIVE LOGITS
     complex
    1.89
    Complex
    1.68
    complex
    1.68
     Complex
    1.61
     COMPLEX
    1.53
     compleja
    1.49
     compless
    1.48
     complexo
    1.45
    COMPLEX
    1.42
     complicated
    1.39
    Act Density 0.024%

    No Known Activations