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

    Neuronpedia

    INDEX
    Explanations

    assigned

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hled
    -0.07
    (parcel
    -0.07
    ophe
    -0.06
    bows
    -0.06
    emit
    -0.06
     decis
    -0.06
     StreamLazy
    -0.06
     Regel
    -0.06
    urdy
    -0.06
     pady
    -0.06
    POSITIVE LOGITS
     assigned
    0.13
     работать
    0.07
     SSR
    0.06
    197
    0.06
    Anything
    0.06
    ĩa
    0.06
     residing
    0.06
    Выб
    0.06
     resident
    0.06
    particularly
    0.06
    Act Density 0.007%

    No Known Activations