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

    Neuronpedia

    INDEX
    Explanations

    repeating characters or syllables in words

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

    Finnish/Swedish/German word endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     them
    -0.43
    onAttach
    -0.41
     tla
    -0.40
    them
    -0.38
     stránka
    -0.38
     objectAtIndex
    -0.37
     Quint
    -0.37
     quarts
    -0.36
    AppCompat
    -0.36
     sess
    -0.36
    POSITIVE LOGITS
    ⓧ
    0.52
    IRQn
    0.48
    այի
    0.46
    asının
    0.46
    HideFlags
    0.46
     Roskov
    0.46
    IContainer
    0.45
    umumkan
    0.45
    ningens
    0.44
    masının
    0.44
    Act Density 0.013%

    No Known Activations