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

    Neuronpedia

    INDEX
    Explanations

    items following numbers or bold text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     grossly
    0.64
     consistently
    0.62
     merely
    0.61
     Throughout
    0.59
     predominantly
    0.59
     Depending
    0.56
     अधिकतर
    0.56
     underwent
    0.56
     unless
    0.55
     जितने
    0.55
    POSITIVE LOGITS
     neutrino
    1.29
     plasma
    1.26
     biodiesel
    1.25
     methane
    1.25
     Plasma
    1.20
     radiotherapy
    1.17
     photovoltaic
    1.17
    Hydroxy
    1.15
    Plasma
    1.13
    plasma
    1.13
    Act Density 0.035%

    No Known Activations