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

    Neuronpedia

    INDEX
    Explanations

    operational definitions and specifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Coun
    0.45
    創作
    0.44
    劉
    0.43
    consulta
    0.43
    頂
    0.43
     consulta
    0.42
    mark
    0.41
     coun
    0.41
    ಿಗ
    0.41
    coco
    0.41
    POSITIVE LOGITS
     ulcer
    0.54
     in
    0.52
     Asthma
    0.52
    laus
    0.48
     वर्षा
    0.48
     Tolerance
    0.47
     Jahre
    0.47
    ·
    0.46
     =)
    0.46
    શ્વ
    0.46
    Act Density 0.001%

    No Known Activations