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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     will
    -0.85
     could
    -0.80
     are
    -0.78
     είναι
    -0.74
     might
    -0.74
     can
    -0.73
     shall
    -0.72
     cannot
    -0.71
     should
    -0.70
     may
    -0.69
    POSITIVE LOGITS
    ThroughAttribute
    0.57
    tvguidetime
    0.54
    principalTable
    0.51
     كومونز
    0.50
    addCriterion
    0.50
    ंदीखरीदारी
    0.49
    NameInMap
    0.47
    MemoryWarning
    0.47
     AssemblyTitle
    0.46
     "..\..\..\
    0.45
    Act Density 0.004%

    No Known Activations