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

    Neuronpedia

    INDEX
    Explanations

    exploit, created, played, log

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     u
    0.47
     gpu
    0.45
     oryg
    0.39
     gmin
    0.39
    पू
    0.39
     Deformation
    0.38
     cercanas
    0.38
     cpu
    0.37
     general
    0.37
    勇气
    0.37
    POSITIVE LOGITS
     તમામ
    0.47
     నిజ
    0.46
     සිය
    0.45
     alcanzar
    0.44
    🥃
    0.44
     தினமும்
    0.44
     subsid
    0.43
    迌
    0.43
    রাষ্ট
    0.43
    olybdenum
    0.43
    Act Density 0.001%

    No Known Activations