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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating hierarchy or positional titles

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

    rank or position following "of"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Chwiliwch
    -0.60
    Personendaten
    -0.53
    setVerticalGroup
    -0.51
     littéraire
    -0.51
    StructEnd
    -0.49
    Kanpo
    -0.46
    parametri
    -0.46
    oa̍t
    -0.45
    Portail
    -0.44
     pontu
    -0.42
    POSITIVE LOGITS
    NOPQRST
    0.49
     Wikimédia
    0.45
    "=>"
    0.45
     làm
    0.44
    ROIT
    0.43
    Hauptartikel
    0.43
    _=
    0.41
     Lead
    0.41
    xmlWriter
    0.41
    bkz
    0.40
    Act Density 0.025%

    No Known Activations