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

    Neuronpedia

    INDEX
    Explanations

    French and German place names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tjiwarl
    0.52
     mislead
    0.49
     makalah
    0.49
    ளாக்
    0.47
     অভাবে
    0.46
    ORITY
    0.45
     Соответ
    0.44
     Significance
    0.44
     വിശദ
    0.43
     సహాయ
    0.43
    POSITIVE LOGITS
     sur
    0.77
    sur
    0.65
     en
    0.59
     le
    0.58
     la
    0.57
     Cedex
    0.57
     les
    0.55
    la
    0.55
    Sur
    0.54
    nombre
    0.54
    Act Density 0.007%

    No Known Activations