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

    Neuronpedia

    INDEX
    Explanations

    how much a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Annotated
    0.43
     connotations
    0.43
     Dere
    0.39
    క్సి
    0.38
    竇
    0.38
     Encourage
    0.37
     Done
    0.37
     Importance
    0.37
     Comparisons
    0.37
     Closeup
    0.36
    POSITIVE LOGITS
     various
    0.65
    various
    0.61
    様々な
    0.60
    那些
    0.56
    ต่างๆ
    0.56
    各種
    0.56
    各类
    0.56
    Various
    0.55
     those
    0.53
     বিভিন্ন
    0.53
    Act Density 0.000%

    No Known Activations