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

    Neuronpedia

    INDEX
    Explanations

    C++ code related to size and types

    oai_token-act-pair · gemini-2.0-flash

    type

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     propOrder
    -0.52
    sizeof
    -0.51
    listdir
    -0.47
    typeof
    -0.46
     transparence
    -0.44
    ErrorListener
    -0.44
     sizeof
    -0.43
    Geografi
    -0.42
     meaningfully
    -0.42
     Wait
    -0.42
    POSITIVE LOGITS
    __":
    0.79
    endphp
    0.77
     CURIAM
    0.69
    
    0.68
    __':
    0.68
    endpush
    0.65
     GenerationType
    0.62
    ToAction
    0.62
    thâu
    0.62
     "..\..\..\
    0.61
    Act Density 1.615%

    No Known Activations