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

    Neuronpedia

    INDEX
    Explanations

    only

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    al
    0.25
    er
    0.24
    ㍍
    0.24
    ۔
    0.23
     anions
    0.22
     excludes
    0.22
     όχι
    0.22
     hormones
    0.22
    ר
    0.22
    uß
    0.21
    POSITIVE LOGITS
    </h2>
    0.25
    1
    0.24
    </i>
    0.22
    ш
    0.21
     приветствовать
    0.20
    ના
    0.20
     пыта
    0.20
    的技术
    0.20
    限于
    0.20
     The
    0.19
    Act Density 0.208%

    No Known Activations