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

    Neuronpedia

    INDEX
    Explanations

    Code/programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     directory
    -0.08
     drž
    -0.07
    /mock
    -0.07
    ollywood
    -0.07
    া�
    -0.07
    “There
    -0.07
     asynchronous
    -0.06
     Positioned
    -0.06
     Senator
    -0.06
    úmeros
    -0.06
    POSITIVE LOGITS
     lạc
    0.06
     UIAlertView
    0.06
     акти
    0.06
    enumerate
    0.06
    нолог
    0.06
     como
    0.06
    inces
    0.06
     frosting
    0.06
    -drop
    0.06
    lsruhe
    0.06
    Act Density 0.020%

    No Known Activations