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

    Neuronpedia

    INDEX
    Explanations

    Numbers and percentages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    是在
    -0.06
     Sid
    -0.06
     sid
    -0.06
    .department
    -0.06
     к
    -0.06
    альных
    -0.06
    del
    -0.06
     colossal
    -0.06
    _fa
    -0.06
    ilim
    -0.06
    POSITIVE LOGITS
     TreeMap
    0.08
     thuyết
    0.07
    .getSimpleName
    0.06
    batis
    0.06
     collider
    0.06
     τι
    0.06
     TreeSet
    0.06
     AppConfig
    0.06
    (stdout
    0.06
    342
    0.06
    Act Density 0.016%

    No Known Activations