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

    Neuronpedia

    INDEX
    Explanations

    ur

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -elected
    -0.07
     hacks
    -0.07
    chants
    -0.07
    inn
    -0.06
     trad
    -0.06
     accounting
    -0.06
     runway
    -0.06
    }-
    -0.06
    _ACT
    -0.06
     repression
    -0.06
    POSITIVE LOGITS
     phil
    0.08
     opět
    0.06
     parcels
    0.06
    Cette
    0.06
    lescope
    0.06
     चल
    0.06
    _Ph
    0.06
     provozu
    0.06
    ）の
    0.06
    threads
    0.06
    Act Density 0.007%

    No Known Activations