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

    Neuronpedia

    INDEX
    Explanations

    vulnerabilities and files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ühr
    0.52
    Hyper
    0.47
    Roi
    0.47
    IR
    0.46
    Vac
    0.45
    asad
    0.44
     দেওয়ার
    0.44
    Authorization
    0.44
     खाली
    0.44
     இருக்கும்
    0.43
    POSITIVE LOGITS
     Breed
    0.44
     iure
    0.42
    韻
    0.41
     leech
    0.40
    辜
    0.40
    ﺘ
    0.40
    室
    0.40
    簡
    0.39
    odeficiency
    0.39
     glorious
    0.38
    Act Density 0.001%

    No Known Activations