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

    Neuronpedia

    INDEX
    Explanations

    locations and entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unamb
    0.21
    GoObject
    0.17
     言っ
    0.16
     operands
    0.16
     offens
    0.16
     تمہ
    0.16
     അയാൾ
    0.16
    ){}
    0.15
     อื่น
    0.15
    },"
    0.15
    POSITIVE LOGITS
     the
    0.29
     The
    0.24
     American
    0.22
     Alliance
    0.22
    The
    0.21
    the
    0.21
     Toronto
    0.21
     C
    0.20
     P
    0.20
     U
    0.20
    Act Density 6.120%

    No Known Activations