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

    Neuronpedia

    INDEX
    Explanations

    names of people and their associated roles or titles

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

    names followed by surnames

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Numerade
    -0.45
    rån
    -0.44
     Photocase
    -0.42
    Lähteet
    -0.41
     Offisielt
    -0.41
     Wikimedijinoj
    -0.40
     Chwiliwch
    -0.40
     Mulher
    -0.40
     Usaha
    -0.40
    utilisons
    -0.39
    POSITIVE LOGITS
    iorna
    0.44
     initComponents
    0.42
    PRF
    0.42
    findpost
    0.41
    InputTagHelper
    0.39
    awaiter
    0.39
     gespannt
    0.38
    hog
    0.38
     Balzac
    0.37
    devamını
    0.36
    Act Density 0.042%

    No Known Activations