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

    Neuronpedia

    INDEX
    Explanations

    names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    دث
    -0.07
    (KeyEvent
    -0.07
    inary
    -0.07
     brewery
    -0.06
     مرک
    -0.06
    _FORE
    -0.06
     Tobacco
    -0.06
    Runnable
    -0.06
    Entropy
    -0.06
    ณะ
    -0.06
    POSITIVE LOGITS
     amounted
    0.06
    +h
    0.06
    	expect
    0.06
     merged
    0.06
    ih
    0.06
    183
    0.06
    ―
    0.06
    educated
    0.06
     شعر
    0.06
    hung
    0.06
    Act Density 0.004%

    No Known Activations