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

    Neuronpedia

    INDEX
    Explanations

    prime

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fon
    -0.07
    References
    -0.06
     bereits
    -0.06
    .should
    -0.06
     rizik
    -0.06
    thickness
    -0.06
     بودند
    -0.06
     dias
    -0.06
    ümüzde
    -0.06
    _pdu
    -0.06
    POSITIVE LOGITS
    Strong
    0.07
                                  ↵
    0.07
                     ↵
    0.06
    �
    0.06
                              ↵
    0.06
    Guy
    0.06
     Hilton
    0.06
     Means
    0.06
    street
    0.06
     Grey
    0.06
    Act Density 0.009%

    No Known Activations