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

    Neuronpedia

    INDEX
    Explanations

    courses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    681
    -0.07
    sn
    -0.07
     者
    -0.07
    rij
    -0.07
    ráci
    -0.07
    oppable
    -0.07
    levance
    -0.07
    bru
    -0.07
    _until
    -0.06
    _channel
    -0.06
    POSITIVE LOGITS
    ’)
    0.07
     поврежд
    0.06
     �
    0.06
    특
    0.06
    _ai
    0.06
     어�
    0.06
    해보
    0.06
     рез
    0.06
     bez
    0.06
    uai
    0.06
    Act Density 0.030%

    No Known Activations