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

    Neuronpedia

    INDEX
    Explanations

    code structure and comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iss
    0.50
     s
    0.46
    eme
    0.45
    ösen
    0.45
     visas
    0.45
    og
    0.45
    ene
    0.44
    ate
    0.44
    ete
    0.43
    ett
    0.43
    POSITIVE LOGITS
     échanc
    0.45
     نعرف
    0.45
    вание
    0.44
     realising
    0.43
     duplicating
    0.43
    toArray
    0.43
    ванных
    0.43
    Ҥ
    0.42
     imitating
    0.42
    mical
    0.42
    Act Density 0.000%

    No Known Activations