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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    constitutional
    -0.06
    (self
    -0.06
     Unter
    -0.06
    Sync
    -0.06
    .generator
    -0.06
     errs
    -0.06
     shelters
    -0.06
     cố
    -0.06
    мага
    -0.06
    TED
    -0.06
    POSITIVE LOGITS
    콩
    0.07
    .Are
    0.07
    toBeTruthy
    0.06
    prisingly
    0.06
     náro
    0.06
     privileges
    0.06
     поля
    0.06
    /tcp
    0.06
    GMT
    0.06
    （笑
    0.06
    Act Density 0.081%

    No Known Activations