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

    Neuronpedia

    INDEX
    Explanations

    numbers and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     şi
    2.05
     flavorful
    1.72
     neighborhoods
    1.65
     postseason
    1.64
    および
    1.63
    ônio
    1.57
     և
    1.54
    >−</
    1.51
     বাড়
    1.49
     nonprofit
    1.49
    POSITIVE LOGITS
     Whilst
    2.58
    Whilst
    2.48
     فى
    2.40
     whilst
    2.35
     £
    2.32
     التى
    2.21
     dodgy
    2.14
     maths
    2.08
     spoilt
    2.08
     apologised
    2.05
    Act Density 0.008%

    No Known Activations