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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Coleman
    -0.08
    تنسيق
    -0.07
    توجيه
    -0.07
     Mechanical
    -0.07
     Omn
    -0.07
    迢
    -0.06
    ystem
    -0.06
    imension
    -0.06
     денег
    -0.06
     идеальн
    -0.06
    POSITIVE LOGITS
    _safe
    0.08
     forum
    0.07
     "*"
    0.07
     helper
    0.07
     pinterest
    0.07
    Press
    0.07
    Queries
    0.06
     belle
    0.06
     fearing
    0.06
    -fetch
    0.06
    Act Density 0.008%

    No Known Activations