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

    Neuronpedia

    INDEX
    Explanations

    VRAM vs. RAM

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    apj
    0.47
    LaTeX
    0.46
    Whitespace
    0.46
    Ray
    0.45
    iii
    0.45
    of
    0.45
    aneous
    0.44
    Jan
    0.44
    (
    0.44
    Tuesday
    0.44
    POSITIVE LOGITS
     émissions
    0.52
    ة
    0.50
     lipoproteins
    0.48
     échanges
    0.47
     М
    0.45
    ций
    0.45
     écart
    0.44
    لمانيا
    0.44
     тепло
    0.44
     manipulations
    0.44
    Act Density 0.000%

    No Known Activations