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

    Neuronpedia

    INDEX
    Explanations

    bold formatting in mathematical expressions

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

    bold m and k notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lenker
    -0.42
     Merz
    -0.40
     campamento
    -0.39
     Curran
    -0.39
     imperio
    -0.39
    ⇄
    -0.38
     useHistory
    -0.38
     Middleton
    -0.37
    Istorija
    -0.37
     препратки
    -0.36
    POSITIVE LOGITS
    bf
    1.62
     bf
    0.74
    textbf
    0.66
    Bf
    0.62
    vif
    0.60
    BF
    0.59
    mathbf
    0.59
    UrlResolution
    0.57
    bibfield
    0.57
    xbf
    0.57
    Act Density 0.024%

    No Known Activations