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

    Neuronpedia

    INDEX
    Explanations

    AWS related

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    brandt
    -0.57
    itar
    -0.56
     Advisor
    -0.56
    xis
    -0.54
    ito
    -0.53
     Dow
    -0.52
    arn
    -0.51
    Advisor
    -0.50
    ido
    -0.49
    Dow
    -0.48
    POSITIVE LOGITS
     Theſe
    0.95
     Monfieur
    0.84
    ✨:
    0.84
     AssemblyTitle
    0.83
     itſelf
    0.82
     myſelf
    0.78
     themſelves
    0.75
     Jefus
    0.75
     becauſe
    0.74
     Efq
    0.72
    Act Density 0.264%

    No Known Activations