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

    Neuronpedia

    INDEX
    Explanations

    measurements and levels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    6
    0.52
     China
    0.48
     richard
    0.43
    5
    0.43
    3
    0.41
    ,"
    0.41
    M
    0.41
     emp
    0.41
    ",
    0.40
     fines
    0.40
    POSITIVE LOGITS
    atthena
    0.49
    ερμαν
    0.48
    اں
    0.47
     tagReport
    0.47
    的一种
    0.45
    nań
    0.45
    焲
    0.45
    وں
    0.45
     перший
    0.45
    ехала
    0.45
    Act Density 0.017%

    No Known Activations