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

    Neuronpedia

    INDEX
    Explanations

    target

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ün
    -0.08
    ROUGH
    -0.07
    _LIBRARY
    -0.07
     dungeons
    -0.07
    io
    -0.07
    rani
    -0.07
     PAGE
    -0.06
     wizards
    -0.06
    IX
    -0.06
     participate
    -0.06
    POSITIVE LOGITS
     /*!<
    0.06
     马
    0.06
     talented
    0.06
    運
    0.06
    single
    0.06
     overs
    0.06
     Endpoint
    0.06
    ництва
    0.06
    .ToDateTime
    0.06
    คโนโลย
    0.06
    Act Density 0.006%

    No Known Activations