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

    Neuronpedia

    INDEX
    Explanations

    immune

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /D
    -0.07
     Aber
    -0.06
     Netherlands
    -0.06
    财
    -0.06
     decoding
    -0.06
     mulher
    -0.06
    _small
    -0.06
     BUFF
    -0.06
     regression
    -0.06
     خور
    -0.06
    POSITIVE LOGITS
    lates
    0.06
    uddled
    0.06
     fossils
    0.06
     Nude
    0.06
     سف
    0.06
    �
    0.06
    qualification
    0.06
    #+
    0.06
     “
    0.06
    ildiği
    0.05
    Act Density 0.013%

    No Known Activations