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

    Neuronpedia

    INDEX
    Explanations

    insightful commentary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Пор
    0.59
    ーカー
    0.51
    ИТ
    0.49
    Res
    0.47
    RC
    0.47
    Purple
    0.46
    BEN
    0.46
    Vet
    0.46
    Е
    0.45
    ದಗ
    0.45
    POSITIVE LOGITS
     saran
    0.48
     в
    0.45
     scala
    0.43
    ่วย
    0.43
     ನಡೆಯ
    0.42
    ments
    0.42
     karma
    0.42
    hljs
    0.42
     tripping
    0.42
     vials
    0.41
    Act Density 0.005%

    No Known Activations