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

    Neuronpedia

    INDEX
    Explanations

    defend the defendant

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    te
    0.40
    chee
    0.39
    zia
    0.39
    February
    0.38
    March
    0.38
    see
    0.38
    story
    0.38
    Steven
    0.38
     Jimenez
    0.37
    Close
    0.37
    POSITIVE LOGITS
     obses
    0.47
     curr
    0.46
     yǒu
    0.45
    ാനുള്ള
    0.43
     ök
    0.42
     osią
    0.42
     tăng
    0.42
    edad
    0.41
    䀼
    0.41
     الآن
    0.41
    Act Density 0.002%

    No Known Activations