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

    Neuronpedia

    INDEX
    Explanations

    to get

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Subsidi
    0.21
     bestowed
    0.20
     nelle
    0.20
     correspondents
    0.20
    🏩
    0.19
     ਹੈ
    0.19
     concedes
    0.19
     equalities
    0.19
     proclaiming
    0.19
     〈
    0.18
    POSITIVE LOGITS
    k
    0.33
    o
    0.28
    er
    0.26
    2
    0.25
    ت
    0.24
    1
    0.23
    ر
    0.23
    i
    0.23
    0
    0.22
    ك
    0.22
    Act Density 0.008%

    No Known Activations