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

    Neuronpedia

    INDEX
    Explanations

    punctuation and mathematical symbols, particularly in numerical contexts

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

    arithmetic expressions or sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+
    -0.40
    RTCK
    -0.38
     '{@
    -0.37
     έκ
    -0.36
    artigen
    -0.33
    EditorGUILayout
    -0.33
    forced
    -0.33
     vraag
    -0.33
    chai
    -0.32
    larg
    -0.31
    POSITIVE LOGITS
    tagHelperRunner
    0.82
    StructEnd
    0.69
    ftagPool
    0.68
     propOrder
    0.68
     Италијани
    0.67
     мәкал
    0.63
     فريبيس
    0.57
    RenderAtEndOf
    0.57
    tagPool
    0.54
    SourceChecksum
    0.53
    Act Density 0.027%

    No Known Activations