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

    Neuronpedia

    INDEX
    Explanations

    NLP, text analysis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     remedies
    -0.08
     Mosque
    -0.08
     secrecy
    -0.08
    理念
    -0.08
    뮤니
    -0.08
     Kobo
    -0.08
     Hiroshima
    -0.07
     Remedies
    -0.07
     Boyle
    -0.07
    ;margin
    -0.07
    POSITIVE LOGITS
     classifications
    0.11
     grammat
    0.11
     classification
    0.10
    分類
    0.10
     grammatical
    0.10
     Annot
    0.10
     класси
    0.10
    Annot
    0.09
    .annot
    0.09
     tagging
    0.09
    Act Density 0.008%

    No Known Activations