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

    Neuronpedia

    INDEX
    Explanations

    factor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     riding
    -0.07
     ragaz
    -0.07
    uyết
    -0.07
    InternalEnumerator
    -0.06
     Leipzig
    -0.06
     governing
    -0.06
     enrich
    -0.06
    with
    -0.06
     dinh
    -0.06
     bli
    -0.06
    POSITIVE LOGITS
    -react
    0.07
    Including
    0.07
    トル
    0.07
    CNT
    0.06
    _expect
    0.06
    เอ
    0.06
    �
    0.06
     //////////////////////////////////////////////////////////////////////
    0.06
     клу
    0.06
    ITTER
    0.06
    Act Density 0.001%

    No Known Activations