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

    Neuronpedia

    INDEX
    Explanations

    code characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     #
    -0.85
     »
    -0.79
    >>
    -0.62
     «
    -0.55
     \#
    -0.54
     "
    -0.50
     ...
    -0.50
    ally
    -0.49
     Pla
    -0.46
     qu
    -0.46
    POSITIVE LOGITS
    +#+#
    0.96
     betweenstory
    0.93
    abestanden
    0.89
    Personendaten
    0.83
     AssemblyProduct
    0.79
    ControllerAdvice
    0.77
    WriteTagHelper
    0.75
    RunWith
    0.75
     متعلقه
    0.73
     насељу
    0.72
    Act Density 0.264%

    No Known Activations