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

    Neuronpedia

    INDEX
    Explanations

    specific terms and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    以及
    0.40
    、
    0.40
    ，
    0.39
    及其
    0.38
    或
    0.38
    麃
    0.38
    嵃
    0.38
    HDMI
    0.36
    参数
    0.36
     και
    0.36
    POSITIVE LOGITS
     localidad
    0.39
     deverá
    0.39
     Pakistan
    0.37
     Kenyan
    0.36
     activist
    0.36
     Venezuela
    0.36
     outpost
    0.35
    ្សែ
    0.35
     ambassador
    0.34
     filho
    0.34
    Act Density 0.001%

    No Known Activations