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

    Neuronpedia

    INDEX
    Explanations

    addresses and numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	address
    -0.08
    Sparse
    -0.07
     chir
    -0.07
    	base
    -0.07
    Minimal
    -0.07
    �y
    -0.07
    ربع
    -0.07
     يونيو
    -0.06
    istrat
    -0.06
    orary
    -0.06
    POSITIVE LOGITS
     -*-↵↵
    0.06
    ollen
    0.06
     صد
    0.06
    (VALUE
    0.06
     snapshot
    0.06
     Kodi
    0.05
     решения
    0.05
    Messenger
    0.05
    fullscreen
    0.05
     �
    0.05
    Act Density 0.003%

    No Known Activations