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

    Neuronpedia

    INDEX
    Explanations

    numeric values, particularly those associated with quantifiable data

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

    01 followed by numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    chaleco
    -0.45
    slidesToShow
    -0.45
    butuhkan
    -0.43
    englanniksi
    -0.42
    TintMode
    -0.41
     burbujas
    -0.41
    atrième
    -0.40
     <<<<<<<<<<<<<<
    -0.39
     receivable
    -0.39
    BufferedWriter
    -0.38
    POSITIVE LOGITS
     désolés
    0.52
    Naissance
    0.50
     considérons
    0.47
    audiovisuel
    0.47
    ErrUnexpectedEOF
    0.44
    1
    0.43
    esModule
    0.43
    st
    0.42
     simplifié
    0.42
    fjspx
    0.42
    Act Density 0.116%

    No Known Activations