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

    Neuronpedia

    INDEX
    Explanations

    Transistor scaling, Moore's law

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     initial
    -0.08
     Mish
    -0.07
    ��
    -0.07
    今
    -0.06
     Parish
    -0.06
    -count
    -0.06
     pueblo
    -0.06
     abstraction
    -0.06
     determined
    -0.06
    _metadata
    -0.06
    POSITIVE LOGITS
     Applies
    0.08
     Von
    0.07
    (fmt
    0.07
    Compatible
    0.07
    Ul
    0.07
    _none
    0.07
    ổi
    0.07
     فقد
    0.07
    越发
    0.07
    兖
    0.07
    Act Density 0.085%

    No Known Activations