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

    Neuronpedia

    INDEX
    Explanations

    titles and names of works or publications

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

    Text or titles starting with "An" or "A"

    np_acts-logits-general · gemini-2.0-flash

    starts of titles or works

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     '\\;'
    -0.65
    SharedDtor
    -0.63
     Italij
    -0.59
    findpost
    -0.58
     RATIO
    -0.57
    expandindo
    -0.57
    帖最后由
    -0.57
     calendriers
    -0.56
     purpoſe
    -0.56
     Salgado
    -0.55
    POSITIVE LOGITS
    🧵
    0.55
    Phaser
    0.51
     tale
    0.48
     puissiez
    0.47
     guide
    0.45
    CORBA
    0.45
    Zdroje
    0.44
    ?..
    0.44
    läg
    0.43
     esternos
    0.42
    Act Density 0.103%

    No Known Activations