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

    Neuronpedia

    INDEX
    Explanations

    identifiers or labels associated with variable or element names

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

    code snippets and variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    less
    -0.36
    可能な
    -0.35
     denominated
    -0.35
     singled
    -0.33
     access
    -0.32
     polarity
    -0.32
     понятно
    -0.31
    ARANCE
    -0.31
     nestled
    -0.31
     capacity
    -0.30
    POSITIVE LOGITS
    tagHelperRunner
    0.79
     pinulongan
    0.72
    rungsseite
    0.72
    httphttps
    0.70
     tartalomajánló
    0.68
     Numerade
    0.64
     betweenstory
    0.58
     estekak
    0.57
    تقاوى
    0.56
     CanadaChoose
    0.55
    Act Density 0.004%

    No Known Activations