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

    Neuronpedia

    INDEX
    Explanations

    statistical sampling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     generations
    -0.08
     ngom
    -0.08
     담
    -0.07
    Generation
    -0.07
     stolen
    -0.07
    dealer
    -0.07
     strained
    -0.07
     flim
    -0.07
     순간
    -0.07
     [{
    -0.07
    POSITIVE LOGITS
     الثلاث
    0.09
     jeweils
    0.09
     dém
    0.09
     Counts
    0.08
    分别
    0.08
     tils
    0.08
     kaj
    0.08
     সরকারের
    0.08
    408
    0.08
    별
    0.08
    Act Density 0.030%

    No Known Activations