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

    Neuronpedia

    INDEX
    Explanations

    references to data structures and conditional checks in programming

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

    Code, equations, and programming-related text

    np_acts-logits-general · gemini-2.0-flash

    Code snippets and diverse punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /**
    -0.40
    arakhand
    -0.37
     <<<<<<<<<<<<<<
    -0.35
    AccessorTable
    -0.35
     duelo
    -0.32
     pouvoirs
    -0.32
    miyor
    -0.30
    consciousness
    -0.30
    }%
    -0.29
     recevrez
    -0.29
    POSITIVE LOGITS
     ब्रेकडाउन
    0.54
    +:+
    0.53
    ftagPool
    0.52
    ScopeManager
    0.50
     ***!
    0.48
     ddelweddau
    0.48
    こんにちは
    0.47
     feltro
    0.46
    脚注の使い方
    0.46
    vician
    0.45
    Act Density 0.269%

    No Known Activations