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

    Neuronpedia

    INDEX
    Explanations

    understanding how

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GID
    0.45
    〕
    0.44
    址
    0.44
    🐛
    0.43
    Ned
    0.41
     AIDS
    0.40
     السوق
    0.40
    NED
    0.40
     oftentimes
    0.39
    ．
    0.39
    POSITIVE LOGITS
    mente
    0.48
    ו
    0.47
     geek
    0.44
     conjoint
    0.44
    étation
    0.44
     startups
    0.43
     about
    0.43
     describe
    0.43
     context
    0.43
     concede
    0.43
    Act Density 0.002%

    No Known Activations