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

    Neuronpedia

    INDEX
    Explanations

    LLM frameworks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ysts
    0.41
    aysia
    0.39
    amburg
    0.38
     Tariff
    0.38
    aires
    0.38
    atius
    0.38
    amily
    0.38
     বক্ত
    0.37
    astly
    0.36
    ecture
    0.36
    POSITIVE LOGITS
    于
    0.41
    AJ
    0.40
    Computed
    0.39
    RJ
    0.39
    lamb
    0.38
     RJ
    0.38
     AJ
    0.38
     Cun
    0.37
    இந்
    0.37
    curricular
    0.36
    Act Density 0.000%

    No Known Activations