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

    Neuronpedia

    INDEX
    Explanations

    measurements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     iod
    -0.07
    硕士学位
    -0.07
    .xml
    -0.06
    .Println
    -0.06
    td
    -0.06
    椀
    -0.06
    implode
    -0.06
     TK
    -0.06
     Ashe
    -0.06
    🐳
    -0.06
    POSITIVE LOGITS
    _buy
    0.07
    _receipt
    0.07
    Humans
    0.07
    �
    0.07
    _Number
    0.07
    uracion
    0.06
    -ground
    0.06
    ∘
    0.06
     organizer
    0.06
    ᅬ
    0.06
    Act Density 0.002%

    No Known Activations