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

    Neuronpedia

    INDEX
    Explanations

    brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    reibung
    -0.06
    \Common
    -0.06
    юн
    -0.06
    ++,
    -0.06
    	In
    -0.06
    ète
    -0.06
    tram
    -0.06
    DOMAIN
    -0.06
    +t
    -0.06
    POSITIVE LOGITS
     [['
    0.09
     ["
    0.08
     OSC
    0.08
     biased
    0.07
     ['
    0.07
     dl
    0.07
     предпоч
    0.07
    _NULL
    0.07
     προϊ
    0.07
     Influ
    0.07
    Act Density 0.015%

    No Known Activations