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

    Neuronpedia

    INDEX
    Explanations

    pronouns and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     détecter
    0.44
     détect
    0.42
     कटोच
    0.42
     primitives
    0.41
     savent
    0.41
     hémorro
    0.40
     rectangles
    0.39
     ublox
    0.39
     detectors
    0.39
     goddesses
    0.39
    POSITIVE LOGITS
    whom
    0.54
     whom
    0.52
    这个人
    0.51
     biographical
    0.51
     biography
    0.49
     Biography
    0.47
    ’
    0.46
     biograf
    0.45
    Biography
    0.44
    𓃵
    0.43
    Act Density 0.179%

    No Known Activations