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

    Neuronpedia

    INDEX
    Explanations

    occurrences of specific acronyms or abbreviations related to names or titles

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

    awned, Winston, Prawn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dike
    -0.47
    codiles
    -0.44
     لينك
    -0.43
    Elsa
    -0.43
     Gadget
    -0.43
     Didi
    -0.43
     Elsa
    -0.42
    paksa
    -0.42
    sweise
    -0.41
    PhysRev
    -0.41
    POSITIVE LOGITS
    wn
    2.56
    WN
    2.16
     wn
    1.59
    Wn
    1.43
     WN
    1.38
    wns
    1.30
    awn
    1.27
    vn
    1.15
    own
    1.03
    wning
    1.02
    Act Density 0.024%

    No Known Activations