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

    Neuronpedia

    INDEX
    Explanations

    results of meetings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lensFlare
    0.47
     israel
    0.44
     gdf
    0.41
     lineales
    0.41
    цу
    0.41
    ADDING
    0.40
     sorpre
    0.40
     dakkh
    0.40
     judíos
    0.40
     nő
    0.40
    POSITIVE LOGITS
     review
    0.46
     आणि
    0.44
     및
    0.43
    以及
    0.41
     proceeding
    0.40
     Evaluation
    0.40
     voting
    0.40
     evaluation
    0.40
     Voting
    0.40
     Procedure
    0.39
    Act Density 0.001%

    No Known Activations