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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -trained
    -0.07
     handbook
    -0.07
    ots
    -0.06
     escap
    -0.06
    ्रदर
    -0.06
    گز
    -0.06
     Leg
    -0.06
    Newsletter
    -0.06
    hari
    -0.06
    кар
    -0.06
    POSITIVE LOGITS
    _oc
    0.07
     відсут
    0.06
    .par
    0.06
     intending
    0.06
    ̀
    0.06
    derived
    0.06
    álního
    0.06
     MA
    0.06
     JFactory
    0.06
    .Date
    0.06
    Act Density 0.340%

    No Known Activations