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

    Neuronpedia

    INDEX
    Explanations

    concepts and choices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    acionales
    0.54
    teilung
    0.52
     نتیجے
    0.50
    utional
    0.50
    র্ঘট
    0.50
    Então
    0.48
    igno
    0.48
    ūsų
    0.47
    Przeczytaj
    0.47
    ți
    0.46
    POSITIVE LOGITS
     allows
    0.53
     ouro
    0.51
     a
    0.50
     accepts
    0.50
     with
    0.50
     priors
    0.50
     DJ
    0.49
     ro
    0.49
     accept
    0.49
     upp
    0.48
    Act Density 0.004%

    No Known Activations