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

    Neuronpedia

    INDEX
    Explanations

    Для

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pax
    -0.07
     vapor
    -0.07
     careers
    -0.07
     ar
    -0.07
     poner
    -0.07
     Snowden
    -0.06
     observer
    -0.06
     ax
    -0.06
     sü
    -0.06
     luder
    -0.06
    POSITIVE LOGITS
     для
    0.09
    ্�
    0.07
    жно
    0.07
    _family
    0.07
    ClassNotFoundException
    0.07
    (gc
    0.07
    _RDONLY
    0.07
    forall
    0.07
    	to
    0.07
     στι
    0.07
    Act Density 0.021%

    No Known Activations