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

    Neuronpedia

    INDEX
    Explanations

    phrases and elements related to research studies and their findings

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

    list of specific phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GOTREF
    -0.59
     AssemblyTitle
    -0.52
     nahilalakip
    -0.51
    libft
    -0.49
    gonic
    -0.48
    ftagPool
    -0.48
     lenker
    -0.48
    fromCharCode
    -0.48
    derung
    -0.46
    gypte
    -0.43
    POSITIVE LOGITS
    Chham
    0.55
    berdayakan
    0.41
     snippetHide
    0.38
     rubrique
    0.37
    roek
    0.35
     atteinte
    0.35
     uží
    0.34
    bibfield
    0.34
     péld
    0.33
     keş
    0.33
    Act Density 0.314%

    No Known Activations