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

    Neuronpedia

    INDEX
    Explanations

    terms related to beta software releases and testing

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

    beta releases or testing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Anliegen
    -0.47
     aranha
    -0.43
     muka
    -0.40
    相关的
    -0.39
    sfx
    -0.39
    Celular
    -0.39
     sostenibilidad
    -0.38
    SetItem
    -0.38
     relevantes
    -0.38
    Related
    -0.38
    POSITIVE LOGITS
    parsedMessage
    0.60
    AISSEE
    0.50
    pushFollow
    0.47
    bitField
    0.45
    互联网档案馆
    0.45
     testers
    0.43
     Subscribers
    0.42
    TypedDataSet
    0.42
     tester
    0.41
    lewati
    0.41
    Act Density 0.010%

    No Known Activations