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

    Neuronpedia

    INDEX
    Explanations

    examples and templates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     poiché
    0.42
     bulunan
    0.39
     poprzez
    0.39
    જના
    0.38
     литератур
    0.38
     Yayın
    0.37
     vielfält
    0.37
     посредством
    0.37
     نہایت
    0.37
    ↡
    0.37
    POSITIVE LOGITS
    USH
    0.40
     bagus
    0.40
    /
    0.40
     us
    0.38
     hobby
    0.38
     fut
    0.38
     ऐप्स
    0.38
    CT
    0.38
    BTW
    0.38
     hardware
    0.38
    Act Density 0.000%

    No Known Activations