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

    Neuronpedia

    INDEX
    Explanations

    punctuation or special characters in a document

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

    foreign language content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.58
     AspNetCore
    -0.51
    /*
    -0.49
    Rüyada
    -0.48
    httphttps
    -0.47
    ValueGenerated
    -0.47
    makeConstraints
    -0.47
     NSCoder
    -0.46
     owne
    -0.46
     Energies
    -0.45
    POSITIVE LOGITS
    OGND
    0.44
     wsi
    0.37
    reszcie
    0.37
    awtextra
    0.34
     phrase
    0.34
     polskiej
    0.34
     laço
    0.34
    InjectMocks
    0.33
     říká
    0.33
     asesinado
    0.32
    Act Density 0.468%

    No Known Activations