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

    Neuronpedia

    INDEX
    Explanations

    structured data with specific naming conventions

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

    dataType definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.75
    transQ
    -0.68
    EndProject
    -0.57
    exitRule
    -0.56
     للمعارف
    -0.53
    ſammen
    -0.49
     pinulongan
    -0.47
    DockStyle
    -0.47
    ɵɵelementEnd
    -0.47
    DeleteBehavior
    -0.46
    POSITIVE LOGITS
     whose
    0.50
    ⁢
    0.49
    Whose
    0.45
    whose
    0.42
    stander
    0.40
     candidate
    0.39
     myel
    0.38
        
    0.38
    enciaga
    0.38
    ainen
    0.37
    Act Density 0.035%

    No Known Activations