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

    Neuronpedia

    INDEX
    Explanations

    auxiliary verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    that
    -0.07
    	that
    -0.06
    ли
    -0.06
    isible
    -0.06
    .travel
    -0.06
     autobi
    -0.06
     This
    -0.06
     ankles
    -0.06
    tickets
    -0.06
    男人
    -0.06
    POSITIVE LOGITS
    َق
    0.07
    sahuje
    0.07
     waypoints
    0.06
     had
    0.06
     вже
    0.06
     返回
    0.06
    Compare
    0.06
     having
    0.06
    reu
    0.06
     quiere
    0.06
    Act Density 0.120%

    No Known Activations