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

    Neuronpedia

    INDEX
    Explanations

    ery

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _table
    -0.07
     bills
    -0.07
     эконом
    -0.07
    �
    -0.07
    ỹ
    -0.07
     Silence
    -0.06
     estate
    -0.06
     Ships
    -0.06
    ниці
    -0.06
     citizenship
    -0.06
    POSITIVE LOGITS
     euch
    0.06
     申博
    0.06
    acc
    0.06
     seiz
    0.06
    _SENT
    0.06
    lte
    0.06
     leo
    0.06
    acent
    0.06
    akter
    0.06
     lanz
    0.06
    Act Density 0.009%

    No Known Activations