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

    Neuronpedia

    INDEX
    Explanations

    algorithmic revolution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     perfectly
    0.51
     parfaitement
    0.50
     кат
    0.47
     Mrs
    0.42
    ্কার
    0.41
     mrs
    0.40
     trataro
    0.40
     taus
    0.40
     perfectamente
    0.39
     puzz
    0.39
    POSITIVE LOGITS
    Jimmy
    0.42
     सितंबर
    0.40
     Opin
    0.38
    জেন
    0.38
    schnitt
    0.37
    ču
    0.36
    erman
    0.36
     Swiss
    0.35
    ১৯
    0.35
    াচিত
    0.35
    Act Density 0.000%

    No Known Activations