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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Her
    -0.07
    нес
    -0.07
    ों
    -0.07
     Doctrine
    -0.07
     Marriage
    -0.07
     kne
    -0.06
    jen
    -0.06
    Realm
    -0.06
     rescue
    -0.06
    'na
    -0.06
    POSITIVE LOGITS
    nement
    0.07
     ZERO
    0.06
    ugins
    0.06
     Indie
    0.06
    ículo
    0.06
     intimidation
    0.05
    596
    0.05
    fox
    0.05
     Printer
    0.05
     chromosomes
    0.05
    Act Density 0.319%

    No Known Activations