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

    Neuronpedia

    INDEX
    Explanations

    instances of the backslash character used for LaTeX commands or environments

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

    start of turn user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -1.03
    хьтан
    -0.86
    delwed
    -0.84
    rungsseite
    -0.82
    Personensuche
    -0.80
    Autoritní
    -0.80
     kaarangay
    -0.79
     disambiguazione
    -0.77
     queſta
    -0.76
    verwijspagina
    -0.75
    POSITIVE LOGITS
    .
    0.38
    čaj
    0.33
    hline
    0.32
     
    0.32
    kla
    0.30
    makeatother
    0.30
     protocol
    0.28
     today
    0.27
     União
    0.27
     fact
    0.27
    Act Density 0.000%

    No Known Activations