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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ">"
    -0.76
    ，“
    -0.71
     '\\
    -0.69
    "<
    -0.68
    "#
    -0.66
    “-
    -0.66
    $"
    -0.65
    endphp
    -0.65
    ”“
    -0.65
    ,"
    -0.64
    POSITIVE LOGITS
     get
    0.49
     hopp
    0.44
    ORAGE
    0.43
    lets
    0.43
     compensate
    0.43
    lengths
    0.43
    Дереккөздер
    0.43
     GenerationType
    0.42
    cipline
    0.41
    whence
    0.41
    Act Density 0.006%

    No Known Activations