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

    Neuronpedia

    INDEX
    Explanations

    population

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     apt
    -0.08
    谑
    -0.07
    .signals
    -0.07
    حرص
    -0.07
    orman
    -0.07
    gable
    -0.07
    喜歡
    -0.07
    出来的
    -0.07
     snapped
    -0.06
    acre
    -0.06
    POSITIVE LOGITS
    มาณ
    0.08
    Entering
    0.08
     CPS
    0.08
     بشأن
    0.07
    켁
    0.07
     repairing
    0.07
     olduğ
    0.07
     현재
    0.07
    .sess
    0.07
     liquidity
    0.07
    Act Density 0.006%

    No Known Activations