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

    Neuronpedia

    INDEX
    Explanations

    terms related to changes, modifications, or alterations

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

    or alternatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Locator
    -0.46
    Cyfarwyddwr
    -0.44
     Grant
    -0.42
     Arri
    -0.42
     LUN
    -0.41
    httphttps
    -0.41
     Calli
    -0.41
     المن
    -0.41
     Covers
    -0.40
     reunion
    -0.40
    POSITIVE LOGITS
    expandindo
    0.58
     <=",
    0.46
    styleable
    0.45
    Datuak
    0.42
    DeleteBehavior
    0.41
     Einfluß
    0.40
     unknownFields
    0.40
    GOTREF
    0.40
    NewLabel
    0.40
    ScopeManager
    0.40
    Act Density 0.126%

    No Known Activations