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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aram
    -0.06
    답
    -0.06
    translate
    -0.06
    ovaného
    -0.06
    etin
    -0.06
    iała
    -0.06
     Coral
    -0.06
    ธาน
    -0.06
     rainfall
    -0.06
     df
    -0.06
    POSITIVE LOGITS
     racing
    0.07
    Now
    0.07
    льт
    0.07
    #else
    0.07
     drafted
    0.07
     lied
    0.07
     ней
    0.07
    /********************************
    0.07
    --------------------------------------------------------------------------↵
    0.06
    _ref
    0.06
    Act Density 0.000%

    No Known Activations