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

    Neuronpedia

    INDEX
    Explanations

    structural markers and emphasis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     logarithmic
    0.31
    Lähteet
    0.31
     nanoscale
    0.31
     spectrophot
    0.30
     multifaceted
    0.30
     optionally
    0.29
     geospatial
    0.29
    ⌵
    0.29
     depicted
    0.29
     hydroxyl
    0.29
    POSITIVE LOGITS
     It
    0.44
     THAT
    0.43
    you
    0.42
    所以我
    0.40
     Nobody
    0.39
     Honestly
    0.39
    Honestly
    0.38
     That
    0.37
     You
    0.36
     If
    0.36
    Act Density 4.273%

    No Known Activations