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

    Neuronpedia

    INDEX
    Explanations

    ening

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     مهر
    -0.07
    著
    -0.07
     chamber
    -0.06
     tit
    -0.06
     ballot
    -0.06
     ensured
    -0.06
     Zwe
    -0.06
    され
    -0.06
    lad
    -0.06
    指导
    -0.06
    POSITIVE LOGITS
    ्भ
    0.07
    μεν
    0.07
     Παρ
    0.06
    льт
    0.06
    culate
    0.06
    issant
    0.06
     shorten
    0.06
    ktop
    0.06
    lectual
    0.06
    щё
    0.06
    Act Density 0.002%

    No Known Activations