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

    Neuronpedia

    INDEX
    Explanations

    lim

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    이라는
    -0.07
    Vs
    -0.07
    우리
    -0.06
    	btn
    -0.06
     pozit
    -0.06
    單
    -0.06
     pai
    -0.06
     positives
    -0.06
     topping
    -0.06
     fruit
    -0.06
    POSITIVE LOGITS
     Estimated
    0.07
     기술
    0.07
     emailAddress
    0.06
     estimated
    0.06
    .setName
    0.06
     beings
    0.06
    (cam
    0.06
     restores
    0.06
    avigator
    0.06
    計劃
    0.06
    Act Density 0.005%

    No Known Activations