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

    Neuronpedia

    INDEX
    Explanations

    this/these followed by a noun/concept

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     a
    0.47
     this
    0.43
    0
    0.43
     the
    0.42
     some
    0.41
     an
    0.40
    '
    0.40
     а
    0.37
    \
    0.34
     \
    0.33
    POSITIVE LOGITS
     particolare
    0.44
     வகையான
    0.38
    玩意
    0.36
     وهذه
    0.36
    particular
    0.36
     tolle
    0.35
    direccion
    0.35
     pesky
    0.35
     süreç
    0.35
     juncture
    0.34
    Act Density 0.087%

    No Known Activations