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

    Neuronpedia

    INDEX
    Explanations

    mathematical formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    え
    -0.08
    宗
    -0.08
     trial
    -0.07
    érons
    -0.07
    Xin
    -0.07
     subjects
    -0.07
    ার্থী
    -0.07
     Dermat
    -0.07
     thema
    -0.07
    752
    -0.06
    POSITIVE LOGITS
     Bons
    0.09
    essa
    0.08
    =*/
    0.08
    leys
    0.08
    .Absolute
    0.08
     ஆசிரிய
    0.08
    irectory
    0.08
     pesta
    0.07
     scarcity
    0.07
     Casablanca
    0.07
    Act Density 0.090%

    No Known Activations