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

    Neuronpedia

    INDEX
    Explanations

    OPKs, US, weights, Ox, step

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ategory
    0.55
     grate
    0.55
    ator
    0.54
     стрельца
    0.54
    robespierre
    0.52
     leukocytes
    0.52
     campfire
    0.51
     신고
    0.51
    Jose
    0.50
     День
    0.50
    POSITIVE LOGITS
    م
    0.70
    ม
    0.55
    س
    0.54
    ين
    0.53
    িস
    0.52
    يم
    0.51
    મ
    0.50
    m
    0.50
    يل
    0.49
    يش
    0.49
    Act Density 0.000%

    No Known Activations