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

    Neuronpedia

    INDEX
    Explanations

    medical research

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     firmware
    -0.07
     science
    -0.07
     latter
    -0.07
    Seller
    -0.07
     مذه
    -0.06
    ibel
    -0.06
    Shield
    -0.06
    Potential
    -0.06
     Cit
    -0.06
     fragile
    -0.06
    POSITIVE LOGITS
    ellation
    0.07
    /red
    0.06
    .getRuntime
    0.06
     khuyến
    0.06
     Hannah
    0.06
     дав
    0.06
    dff
    0.06
    .increment
    0.06
    لاین
    0.06
    adal
    0.06
    Act Density 0.069%

    No Known Activations