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

    Neuronpedia

    INDEX
    Explanations

    changing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     בנושא
    -0.07
     CALC
    -0.07
     EF
    -0.06
    โด
    -0.06
    xEF
    -0.06
     Prod
    -0.06
    (hand
    -0.06
    ΅
    -0.06
     Eff
    -0.06
    (insert
    -0.06
    POSITIVE LOGITS
    ומות
    0.07
    宫殿
    0.07
    三农
    0.07
     Trọng
    0.07
    qq
    0.06
     Agricultural
    0.06
    _Str
    0.06
    vas
    0.06
     followers
    0.06
    culture
    0.06
    Act Density 0.021%

    No Known Activations