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

    Neuronpedia

    INDEX
    Explanations

    programming constructs that indicate function calls and data structures

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

    Code snippets and programming terms

    np_acts-logits-general · gemini-2.0-flash

    code structures and data types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EndContext
    -0.61
    aritions
    -0.54
     ModelExpression
    -0.54
    homonymie
    -0.52
     Sarm
    -0.49
    ChildScrollView
    -0.48
     park
    -0.47
     geslacht
    -0.46
    cham
    -0.45
    цездатний
    -0.45
    POSITIVE LOGITS
    +#+
    0.77
     vPvB
    0.66
     Audiodateien
    0.64
    MetaType
    0.63
    Rohy
    0.61
     ویکی‌پدیا
    0.59
    elemField
    0.55
    }))
    0.53
    ]")]
    0.53
    SBATCH
    0.52
    Act Density 0.332%

    No Known Activations