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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.84
     ſeveral
    -0.77
     Efq
    -0.76
     a
    -0.75
     Eſ
    -0.73
     neceffary
    -0.72
     whoſe
    -0.70
     Theſe
    -0.69
     ſtate
    -0.68
     ſmall
    -0.67
    POSITIVE LOGITS
    出版年
    0.54
    AndEndTag
    0.52
    ectady
    0.44
    WriteTagHelper
    0.43
     Infórmanos
    0.43
    LLocation
    0.41
    SerializedName
    0.41
     externi
    0.40
    مراجع
    0.37
    invokeLater
    0.37
    Act Density 0.004%

    No Known Activations