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

    Neuronpedia

    INDEX
    Explanations

    code and configurations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    MBER
    -0.07
    ooting
    -0.07
    global
    -0.07
    435
    -0.06
    114
    -0.06
    _EXIT
    -0.06
    asy
    -0.06
     remember
    -0.06
    ेह
    -0.06
     CHANGE
    -0.06
    POSITIVE LOGITS
     Describe
    0.07
     giành
    0.06
     cig
    0.06
     влади
    0.06
    _tls
    0.06
     تاث
    0.06
     symmetric
    0.06
    吴
    0.06
     наяв
    0.06
     loại
    0.06
    Act Density 0.000%

    No Known Activations