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

    Neuronpedia

    INDEX
    Explanations

    conclusion after calculation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     và
    0.52
     and
    0.47
    và
    0.47
     Celebrity
    0.45
     Và
    0.45
     Kiểm
    0.45
     implies
    0.44
     Mobile
    0.44
     கால்
    0.44
     Mobility
    0.44
    POSITIVE LOGITS
    答え
    0.40
    Bright
    0.39
    ሏ
    0.39
    ំនួន
    0.38
    ദ്ധതി
    0.38
    addington
    0.38
    граф
    0.37
    ToPlot
    0.37
    acterial
    0.36
    Delhi
    0.36
    Act Density 0.010%

    No Known Activations