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

    Neuronpedia

    INDEX
    Explanations

    Polish language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     shepherd
    -0.07
     �
    -0.06
     préc
    -0.06
    ریان
    -0.06
     bends
    -0.06
     ringing
    -0.06
    σίας
    -0.06
     Straw
    -0.06
     aroused
    -0.06
     üretim
    -0.06
    POSITIVE LOGITS
    (trace
    0.07
     Ethan
    0.07
    inally
    0.07
    _THAN
    0.06
     NATO
    0.06
     resend
    0.06
     ZEND
    0.06
    строй
    0.06
    _HISTORY
    0.06
     ':'
    0.06
    Act Density 0.155%

    No Known Activations