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

    Neuronpedia

    INDEX
    Explanations

    technical terms and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Em
    0.57
    Carlton
    0.50
    ោះស្រាយ
    0.50
    Il
    0.49
    J
    0.48
    Add
    0.47
    Eat
    0.46
    Econom
    0.46
    Eine
    0.45
    ADD
    0.45
    POSITIVE LOGITS
    lamualaikum
    0.47
     były
    0.45
    <unused2>
    0.45
     serían
    0.45
    kých
    0.43
     CSV
    0.42
     spp
    0.42
     flurry
    0.42
    ovaných
    0.41
     современ
    0.41
    Act Density 0.001%

    No Known Activations