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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    子供
    -0.07
    سمة
    -0.07
     Feet
    -0.06
     několika
    -0.06
     Survival
    -0.06
     馬
    -0.06
    जन
    -0.06
     замов
    -0.06
     увелич
    -0.06
    ppy
    -0.06
    POSITIVE LOGITS
    GetX
    0.07
    _Log
    0.06
     predict
    0.06
     ={
    0.06
     Philosoph
    0.06
    (document
    0.06
     connects
    0.06
    999
    0.06
    اخته
    0.06
    _phy
    0.06
    Act Density 0.007%

    No Known Activations