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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ____
    -0.07
     Hz
    -0.07
     Schema
    -0.07
     burden
    -0.07
    \Collection
    -0.06
    Backing
    -0.06
    Manager
    -0.06
    orWhere
    -0.06
    上了
    -0.06
     vielen
    -0.06
    POSITIVE LOGITS
    Keith
    0.07
     你
    0.07
     Keith
    0.07
     rej
    0.06
     IPs
    0.06
    _em
    0.06
     disse
    0.06
    _reports
    0.06
    _nat
    0.06
    ﾏ
    0.06
    Act Density 0.000%

    No Known Activations