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

    Neuronpedia

    INDEX
    Explanations

    say "("

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CON
    -0.07
    square
    -0.07
    Configuration
    -0.07
    _icon
    -0.06
    Intent
    -0.06
    Cloud
    -0.06
     Ul
    -0.06
    .con
    -0.06
    Ignore
    -0.06
    .COM
    -0.06
    POSITIVE LOGITS
    풋
    0.07
    颢
    0.07
     física
    0.07
    三位一体
    0.07
     Trey
    0.07
     apo
    0.07
     CHtml
    0.07
    砺
    0.07
    ﾃ
    0.07
    斥
    0.07
    Act Density 0.013%

    No Known Activations