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

    Neuronpedia

    INDEX
    Explanations

    references to online articles and supplementary materials associated with academic publications

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

    supplementary material

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Schaefer
    -0.43
     CAPACITY
    -0.40
     Dör
    -0.39
     CANDIDATE
    -0.38
     Internal
    -0.37
    othek
    -0.37
     McBride
    -0.36
     Ol
    -0.36
     Sar
    -0.35
     Schmitz
    -0.35
    POSITIVE LOGITS
     EconPapers
    0.96
    Tikang
    0.73
    tagHelperRunner
    0.69
     autorytatywna
    0.67
    DockStyle
    0.66
     Roskov
    0.66
     informée
    0.62
    httphttps
    0.61
    ThroughAttribute
    0.61
    Искәрмәләр
    0.60
    Act Density 0.008%

    No Known Activations