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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.06
    _extended
    -0.06
    Consumer
    -0.06
    LinearLayout
    -0.06
     степени
    -0.06
    posure
    -0.06
    itize
    -0.06
     manžel
    -0.06
    dě
    -0.06
    ντ
    -0.06
    POSITIVE LOGITS
    toolbox
    0.07
    .What
    0.07
     troub
    0.07
     Holmes
    0.07
    Miami
    0.06
    uyết
    0.06
    タイ
    0.06
    ，再
    0.06
     engagements
    0.06
    .C
    0.06
    Act Density 0.030%

    No Known Activations