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

    Neuronpedia

    INDEX
    Explanations

    mathematical parameters and variables related to functions

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

    epsilon notation in mathematical expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -0.49
    Hentet
    -0.49
    ometric
    -0.49
    omeness
    -0.42
    clerView
    -0.42
     alar
    -0.42
     Oxid
    -0.41
    disse
    -0.40
     Optimis
    -0.40
     OPTIM
    -0.40
    POSITIVE LOGITS
     '\\;'
    0.63
     itſelf
    0.56
     disambiguazione
    0.48
    Dichloropropane
    0.41
     himſelf
    0.40
     alike
    0.39
    PerformLayout
    0.38
     Serikat
    0.37
     ilman
    0.37
     poffible
    0.37
    Act Density 0.069%

    No Known Activations