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

    Neuronpedia

    INDEX
    Explanations

    possibility

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reversal
    -0.06
    ############################################################
    -0.06
    StdString
    -0.06
    urrence
    -0.06
    Processing
    -0.06
    idebar
    -0.06
    .getName
    -0.06
    Former
    -0.05
    Math
    -0.05
     Earlier
    -0.05
    POSITIVE LOGITS
     ServiceException
    0.07
     kontakte
    0.07
    ("[
    0.07
     mehr
    0.06
         
    0.06
     ölçüde
    0.06
     эту
    0.06
    στο
    0.06
    ("{
    0.06
     отверсти
    0.06
    Act Density 0.028%

    No Known Activations