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

    Neuronpedia

    INDEX
    Explanations

    &

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Stored
    -0.07
    311
    -0.06
     Oculus
    -0.06
     أخ
    -0.06
    ozor
    -0.06
     mListener
    -0.06
     inex
    -0.06
     ".$_
    -0.06
     Hàng
    -0.06
     Supplements
    -0.06
    POSITIVE LOGITS
    敵
    0.08
    confidence
    0.07
    ATT
    0.07
     turtles
    0.07
     обличчя
    0.07
    ulled
    0.07
    TECT
    0.07
     qualities
    0.07
     DRIVE
    0.07
     labels
    0.06
    Act Density 0.001%

    No Known Activations