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

    Neuronpedia

    INDEX
    Explanations

    mathematical notations and symbols typically used in equations or proofs

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

    mathematical notation or citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enumii
    -0.64
    DockStyle
    -0.63
     arşivlendi
    -0.61
    AnchorStyles
    -0.58
     مرئيه
    -0.54
    SharedCtor
    -0.54
    AutoScaleMode
    -0.53
    DataAnnotations
    -0.51
    complexContent
    -0.49
     saites
    -0.47
    POSITIVE LOGITS
     ब्रेकडाउन
    0.52
    jiga
    0.38
     stanga
    0.37
    adaptiveStyles
    0.36
     pysty
    0.36
    hood
    0.35
    jde
    0.35
     nationales
    0.34
    RegressionTest
    0.34
     CURIAM
    0.33
    Act Density 0.457%

    No Known Activations