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

    Neuronpedia

    INDEX
    Explanations

    i

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	ULONG
    -0.07
     Ambassador
    -0.06
    AO
    -0.06
    dehyde
    -0.06
    šker
    -0.06
    _neighbors
    -0.06
    -cookie
    -0.06
    VICES
    -0.06
    기의
    -0.06
    (Socket
    -0.06
    POSITIVE LOGITS
    atism
    0.08
     senator
    0.07
     whispered
    0.07
     blasted
    0.07
     Vin
    0.06
     grind
    0.06
    혀
    0.06
     serge
    0.06
     \
↵
    0.06
     MICRO
    0.06
    Act Density 0.007%

    No Known Activations