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

    Neuronpedia

    INDEX
    Explanations

    Organizations and locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     whats
    -0.06
     infect
    -0.06
     Basket
    -0.06
    ashi
    -0.06
     назива
    -0.06
     connector
    -0.06
     comprom
    -0.06
     skull
    -0.06
    (Settings
    -0.06
    bagai
    -0.06
    POSITIVE LOGITS
     countries
    0.08
    oire
    0.07
    ton
    0.07
     إ
    0.06
    ichte
    0.06
     extradition
    0.06
     Buf
    0.06
    Iter
    0.06
     portrayal
    0.06
    ener
    0.06
    Act Density 0.029%

    No Known Activations