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
    _HOT
    -0.07
     Basics
    -0.07
     SIZE
    -0.06
    这项
    -0.06
    adoras
    -0.06
    sequence
    -0.06
     gaining
    -0.06
    Chem
    -0.06
    _RAM
    -0.06
    Sony
    -0.06
    POSITIVE LOGITS
    祸
    0.07
     Johannes
    0.07
    釐
    0.07
     pav
    0.06
    _decor
    0.06
    뇽
    0.06
    固定的
    0.06
     comando
    0.06
     comment
    0.06
     Turnbull
    0.06
    Act Density 0.029%

    No Known Activations