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

    Neuronpedia

    INDEX
    Explanations

    could can

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bioaccumulative
    -0.48
     even
    -0.45
     also
    -0.43
    even
    -0.43
     indeed
    -0.43
    )}-\
    -0.39
     incluso
    -0.38
     sogar
    -0.38
    كما
    -0.38
     zelfs
    -0.37
    POSITIVE LOGITS
    parsedMessage
    1.03
    MigrationBuilder
    0.94
     للاسماء
    0.84
    LookAnd
    0.83
    EndContext
    0.81
    WireFormatLite
    0.77
     springfox
    0.76
     please
    0.75
    MethodManager
    0.75
     bitte
    0.71
    Act Density 0.006%

    No Known Activations