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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate conditionality or possibility

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

    parts of things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AccessorTable
    -0.51
     referrerpolicy
    -0.50
     typelib
    -0.50
     BrowserRouter
    -0.48
    streifen
    -0.47
    GEBURTSDATUM
    -0.46
    contentLoaded
    -0.45
    CPtr
    -0.43
    schirm
    -0.43
    󠁴
    -0.43
    POSITIVE LOGITS
    جوايز
    0.40
    kuuta
    0.39
    licted
    0.38
    SupportActionBar
    0.38
    ticing
    0.38
    доми
    0.37
     yym
    0.37
    Cormack
    0.37
    lgari
    0.37
     waaronder
    0.36
    Act Density 0.100%

    No Known Activations