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

    Neuronpedia

    INDEX
    Explanations

    "he said" phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Remove
    0.22
     crabs
    0.22
     birch
    0.21
     제거
    0.21
    ".
    0.21
     restart
    0.21
     crab
    0.21
     phytoplankton
    0.21
     हटा
    0.21
     przetwarz
    0.21
    POSITIVE LOGITS
    他說
    0.42
    says
    0.41
    他说
    0.40
    她说
    0.38
     says
    0.35
    said
    0.34
    다라고
    0.33
    说
    0.33
     يقول
    0.32
     zegt
    0.32
    Act Density 0.021%

    No Known Activations