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

    Neuronpedia

    INDEX
    Explanations

    references to subjects

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cars
    -0.07
    Bir
    -0.06
    ecture
    -0.06
    RefCount
    -0.06
     αντι
    -0.06
    和
    -0.06
    بعد
    -0.06
    moduleId
    -0.06
     bitter
    -0.06
     DELETE
    -0.06
    POSITIVE LOGITS
    ΑΓ
    0.06
    оля
    0.06
    宗
    0.06
     prům
    0.06
     owes
    0.06
     decad
    0.06
     famously
    0.06
    _tip
    0.06
     Crimes
    0.05
     Lemma
    0.05
    Act Density 0.118%

    No Known Activations