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

    Neuronpedia

    INDEX
    Explanations

    the beginning of a document or a section of text

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

    Text following "Q" or parentheses

    np_acts-logits-general · gemini-2.0-flash

    policy digest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ujednoznacz
    -0.85
     defaultstate
    -0.78
    .*")]
    -0.77
     protoimpl
    -0.68
    abestanden
    -0.67
     ***!
    -0.65
    verwijspagina
    -0.64
     linkovi
    -0.63
     Lijst
    -0.63
    enumi
    -0.63
    POSITIVE LOGITS
    喺
    0.71
    嘅
    0.71
    佢
    0.63
    ďaka
    0.60
    係
    0.60
    咁
    0.60
    咗
    0.59
     bahawa
    0.58
    好似
    0.58
     aikaa
    0.57
    Act Density 0.034%

    No Known Activations