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

    Neuronpedia

    INDEX
    Explanations

    references to research studies and their methodology

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

    languages and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.50
    -0.42
    awtextra
    -0.41
    httphttps
    -0.40
    لينكات
    -0.40
    homonymie
    -0.37
    vician
    -0.36
    ⟬
    -0.36
     wobec
    -0.35
    twimg
    -0.35
    POSITIVE LOGITS
     in
    0.98
     expressed
    0.67
     denominated
    0.66
    expressed
    0.60
     written
    0.56
     σε
    0.53
     express
    0.52
     بال
    0.52
     بالع
    0.50
     exprim
    0.50
    Act Density 0.125%

    No Known Activations