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

    Neuronpedia

    INDEX
    Explanations

    answer to questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    smanship
    1.76
    na
    1.58
     सारी
    1.56
     floribus
    1.56
    ्य
    1.54
    जिन
    1.53
    ์
    1.53
    ת
    1.52
     manhã
    1.47
    芑
    1.45
    POSITIVE LOGITS
    ike
    1.33
    傅
    1.30
    ut
    1.30
    utin
    1.25
    ate
    1.24
    ങ്ങൾ
    1.20
    엥
    1.20
    acks
    1.19
    swering
    1.19
     suscit
    1.19
    Act Density 0.793%

    No Known Activations