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

    Neuronpedia

    INDEX
    Explanations

    appearances versus reality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Versions
    -0.07
    коном
    -0.07
    emouth
    -0.06
     plav
    -0.06
    Bear
    -0.06
    MouseDown
    -0.06
     absorbs
    -0.06
    させる
    -0.06
     빌
    -0.06
    .tipo
    -0.06
    POSITIVE LOGITS
    ("/{
    0.07
    通过
    0.07
    	synchronized
    0.06
     atte
    0.06
    .parseDouble
    0.06
    同步
    0.06
    bris
    0.06
     在
    0.06
     dor
    0.06
     QList
    0.06
    Act Density 0.139%

    No Known Activations