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

    Neuronpedia

    INDEX
    Explanations

    .jpg

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     )"
    -0.07
     ))
    -0.07
     embarked
    -0.06
     Sensors
    -0.06
     Quarter
    -0.06
     popped
    -0.06
    )));
    -0.06
     expans
    -0.06
     _.
    -0.06
    ))))
    -0.06
    POSITIVE LOGITS
    filename
    0.07
    ní
    0.07
     anonymity
    0.06
     bekommen
    0.06
    tright
    0.06
    _post
    0.06
    ilet
    0.06
     фундамент
    0.06
     виход
    0.06
     Sms
    0.06
    Act Density 0.000%

    No Known Activations