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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    InjectAttribute
    -0.74
     EconPapers
    -0.66
    はじめに
    -0.65
     "..\..\
    -0.65
    ⓧ
    -0.63
     "..\..\..\
    -0.62
    )";
    -0.61
    httphttps
    -0.61
     initComponents
    -0.59
    SPATH
    -0.59
    POSITIVE LOGITS
    Smarty
    0.52
     adaptarse
    0.48
     instead
    0.47
     worse
    0.47
    Gizmos
    0.46
     blaming
    0.45
     incompatible
    0.45
    word
    0.44
    Word
    0.43
     fondamental
    0.43
    Act Density 0.006%

    No Known Activations