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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rightfully
    -0.07
     PHY
    -0.06
    스가
    -0.06
     apology
    -0.06
    当然
    -0.06
     degrade
    -0.06
    แสง
    -0.06
    vají
    -0.06
    अब
    -0.06
     celý
    -0.06
    POSITIVE LOGITS
    _entry
    0.06
    :size
    0.06
    /action
    0.06
    _BTN
    0.06
    .engine
    0.06
     multid
    0.06
    Tools
    0.06
     المس
    0.06
     Shot
    0.06
    .ReLU
    0.06
    Act Density 0.701%

    No Known Activations