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

    Neuronpedia

    INDEX
    Explanations

    throughout

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     throughout
    -0.98
    throughout
    -0.97
     Throughout
    -0.82
    Throughout
    -0.79
     THRO
    -0.71
    MergeFrom
    -0.64
    ñores
    -0.62
    ÚBL
    -0.60
    engertian
    -0.60
     photolibrary
    -0.60
    POSITIVE LOGITS
     the
    0.93
     your
    0.75
     an
    0.62
     my
    0.60
    تقاوى
    0.58
    /*---
    0.58
    setVerticalGroup
    0.56
     our
    0.56
     pinulongan
    0.55
     so
    0.53
    Act Density 0.034%

    No Known Activations