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

    Neuronpedia

    INDEX
    Explanations

    sequences that represent alphanumeric codes or versions

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

    URL fragments and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     houſe
    -0.64
     Houſe
    -0.63
     NSCoder
    -0.61
     ſta
    -0.60
     виправивши
    -0.59
     nonUne
    -0.58
    RenderAtEndOf
    -0.57
     himo
    -0.57
    angliski
    -0.56
     ſche
    -0.56
    POSITIVE LOGITS
    estacks
    0.36
     Roskov
    0.35
    Erstellt
    0.35
    Instagram
    0.28
     doel
    0.28
     gönder
    0.27
    complexContent
    0.26
    今日の
    0.26
    Filmografie
    0.26
     Instagram
    0.26
    Act Density 0.000%

    No Known Activations