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

    Neuronpedia

    INDEX
    Explanations

    things just

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    បែប
    0.44
    ü
    0.43
    ன்ஹீ
    0.43
    HER
    0.42
    üman
    0.41
    ੂ
    0.40
    UNESCO
    0.40
     куда
    0.39
    GetComponent
    0.39
    参数
    0.38
    POSITIVE LOGITS
    ._
    0.55
     salvaged
    0.41
     shirt
    0.41
    .`
    0.41
     مفت
    0.40
     Carson
    0.40
     মাত
    0.40
     theyre
    0.40
     rallied
    0.39
     petite
    0.39
    Act Density 0.004%

    No Known Activations