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

    Neuronpedia

    INDEX
    Explanations

    bio and web links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    нование
    -0.81
     multer
    -0.75
     esempio
    -0.75
    ئت
    -0.73
     Walton
    -0.71
    endalikan
    -0.70
    たたみ
    -0.69
     schlug
    -0.69
    并未
    -0.69
    xhttp
    -0.68
    POSITIVE LOGITS
     bio
    1.96
     link
    1.64
     Link
    1.61
    bio
    1.54
    link
    1.52
    BIO
    1.36
     био
    1.35
    Link
    1.30
     Bio
    1.26
    Bio
    1.25
    Act Density 0.011%

    No Known Activations