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

    Neuronpedia

    INDEX
    Explanations

    references to research findings and claims

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

    words after "the"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     flota
    -0.45
     Administrativna
    -0.38
     podjela
    -0.37
    ButtonItem
    -0.36
     autorytatywna
    -0.36
     cerâmica
    -0.35
    ategorias
    -0.35
    ValueStyle
    -0.34
     landing
    -0.34
     collections
    -0.34
    POSITIVE LOGITS
    UserScript
    0.52
    principalTable
    0.52
     المعيارى
    0.51
    bkz
    0.50
     تضيفلها
    0.49
     ſhe
    0.49
    #
    0.48
     Majefty
    0.47
     itſelf
    0.47
    wußt
    0.46
    Act Density 0.007%

    No Known Activations