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

    Neuronpedia

    INDEX
    Explanations

    relevant

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     the
    -0.48
     
    -0.48
     since
    -0.47
    dalla
    -0.45
     just
    -0.45
    <eos>
    -0.43
     gesehen
    -0.43
    nél
    -0.42
     that
    -0.42
     likely
    -0.42
    POSITIVE LOGITS
     مرئيه
    1.05
     defaultstate
    0.98
    DockStyle
    0.88
     oprot
    0.87
    FunctionFlags
    0.85
    MigrationBuilder
    0.84
     disambiguazione
    0.84
    SourceChecksum
    0.83
     дописавши
    0.82
    EDEFAULT
    0.81
    Act Density 0.014%

    No Known Activations