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

    Neuronpedia

    INDEX
    Explanations

    code and data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ARC
    -0.07
    130
    -0.07
    129
    -0.06
    mits
    -0.06
    309
    -0.06
    ほ
    -0.06
    ặn
    -0.06
    rub
    -0.06
    126
    -0.06
    CRC
    -0.06
    POSITIVE LOGITS
    А
    0.06
     };↵
    0.06
    _elem
    0.06
    _JOIN
    0.06
     freopen
    0.06
     Marvel
    0.06
    WithContext
    0.06
    ODULE
    0.06
    aviors
    0.06
     cutoff
    0.06
    Act Density 0.015%

    No Known Activations