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

    Neuronpedia

    INDEX
    Explanations

    code-related elements or constructs in programming contexts

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

    This code, then explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.68
    RenderAtEndOf
    -0.56
    ftagPool
    -0.50
    tagHelperRunner
    -0.48
    TagMode
    -0.48
    oa̍t
    -0.48
     незавершена
    -0.47
    المناصب
    -0.47
     geholfen
    -0.46
    Tikang
    -0.44
    POSITIVE LOGITS
    PYX
    0.41
    vily
    0.38
     coded
    0.38
    0.38
     shortage
    0.37
    enservice
    0.37
     виправивши
    0.37
     setuptools
    0.36
    encoj
    0.36
     schen
    0.35
    Act Density 0.005%

    No Known Activations