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

    Neuronpedia

    INDEX
    Explanations

    classified information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     squir
    0.31
     ESPN
    0.30
    ্ত্র
    0.30
    క్య
    0.30
     క్యా
    0.30
    Ϣ
    0.30
    尴尬
    0.29
     లేదా
    0.29
    尴
    0.29
    ┕
    0.29
    POSITIVE LOGITS
     nuovi
    0.34
    mechan
    0.32
     auxquels
    0.30
    OGRAF
    0.29
    Soviet
    0.29
    OMA
    0.29
     nuovo
    0.29
     bunda
    0.29
     idee
    0.29
    ute
    0.28
    Act Density 0.000%

    No Known Activations