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

    Neuronpedia

    INDEX
    Explanations

    not just, access, beginning, blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    كت
    0.52
     ένα
    0.51
     один
    0.51
    ichts
    0.49
     கலோரிகள்
    0.48
    ਕਰ
    0.46
    ่
    0.46
     jedan
    0.46
    hme
    0.46
    謖
    0.45
    POSITIVE LOGITS
     rejection
    0.45
    ᖕ
    0.45
     midnight
    0.44
     software
    0.41
     divid
    0.41
     نبود
    0.40
     sci
    0.39
    凌晨
    0.38
     aktor
    0.38
     weekend
    0.38
    Act Density 0.005%

    No Known Activations