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

    Neuronpedia

    INDEX
    Explanations

    recipe yield

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LOTREntity
    0.38
    الس
    0.36
     граф
    0.35
    高品質
    0.35
    桝
    0.35
     trattano
    0.34
    Ду
    0.33
    𝔀
    0.33
    อะคาเดมี
    0.33
    gmzy
    0.33
    POSITIVE LOGITS
     findings
    0.37
     FTA
    0.36
    findings
    0.35
     }*/
    0.35
     Findings
    0.35
     dynam
    0.34
    ff
    0.33
    4
    0.33
     Lalu
    0.33
     Gita
    0.33
    Act Density 0.006%

    No Known Activations