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

    Neuronpedia

    INDEX
    Explanations

    software licenses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :
    0.73
    Quando
    0.72
     Agents
    0.66
     Empowerment
    0.66
    quando
    0.65
    Environmental
    0.63
     Bridges
    0.62
     প্রোগ্র
    0.62
    媢
    0.62
    WHEN
    0.62
    POSITIVE LOGITS
    0.66
     placard
    0.61
     haline
    0.59
     vague
    0.58
     daar
    0.57
     bagno
    0.55
     drugi
    0.55
    ارى
    0.55
     başında
    0.55
     sağ
    0.54
    Act Density 0.001%

    No Known Activations