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

    Neuronpedia

    INDEX
    Explanations

    list formatting symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     สุด
    0.52
     Fatima
    0.52
    朼
    0.48
     Tang
    0.47
     Haar
    0.47
     Beirut
    0.47
    婵
    0.47
     Harlem
    0.46
     Srinagar
    0.46
     pran
    0.46
    POSITIVE LOGITS
    ᱣ
    0.52
    ໊
    0.52
    ਠ
    0.50
    ф
    0.47
    チ
    0.47
     algu
    0.47
    Yep
    0.46
    দের
    0.46
     совпада
    0.46
    Pooled
    0.46
    Act Density 0.000%

    No Known Activations