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

    Neuronpedia

    INDEX
    Explanations

    stated definition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    verbal
    0.50
     Verbal
    0.47
     verbal
    0.46
     ধারনা
    0.44
    詳しい
    0.42
    有两个
    0.41
    ત
    0.40
     verbally
    0.40
    وسع
    0.39
    Speech
    0.38
    POSITIVE LOGITS
     describing
    0.69
     “[
    0.67
     referring
    0.64
     “…
    0.64
     exclaimed
    0.63
     regarding
    0.62
     comparing
    0.62
     concerning
    0.57
     replying
    0.57
     Referring
    0.56
    Act Density 0.027%

    No Known Activations