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

    Neuronpedia

    INDEX
    Explanations

    specification

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ngữ
    -0.07
    _Invoke
    -0.07
     соглас
    -0.07
    군요
    -0.06
     böylece
    -0.06
     lập
    -0.06
    比例
    -0.06
     호출
    -0.06
    .transforms
    -0.06
     उम
    -0.06
    POSITIVE LOGITS
    Pr
    0.06
     Thailand
    0.06
    paste
    0.06
    .Fetch
    0.06
     Vegetable
    0.06
    913
    0.06
    _are
    0.06
    ?=
    0.06
    trace
    0.06
    .iterator
    0.06
    Act Density 0.005%

    No Known Activations