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

    Neuronpedia

    INDEX
    Explanations

    mouth

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     účast
    -0.07
    _rad
    -0.07
     Adri
    -0.07
    Rad
    -0.07
    Ã
    -0.06
     Refugee
    -0.06
    政
    -0.06
    难
    -0.06
     Zend
    -0.06
     ци
    -0.06
    POSITIVE LOGITS
     mouth
    0.12
     mouths
    0.10
    -mouth
    0.09
     Mouth
    0.08
    mouth
    0.08
    ARTH
    0.08
    ��
    0.08
    rowning
    0.07
    口
    0.07
    орт
    0.07
    Act Density 0.007%

    No Known Activations