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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     более
    -0.07
     ↵ ↵
    -0.07
    info
    -0.06
    Error
    -0.06
    ERC
    -0.06
    部门
    -0.06
    IRTUAL
    -0.06
    DL
    -0.06
    cls
    -0.06
    urgence
    -0.06
    POSITIVE LOGITS
     nuis
    0.07
     Jerusalem
    0.07
     coil
    0.07
     ELF
    0.06
    _AD
    0.06
    	df
    0.06
     unity
    0.06
     alertDialog
    0.06
     yourself
    0.06
    âk
    0.06
    Act Density 0.016%

    No Known Activations