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

    Neuronpedia

    INDEX
    Explanations

    Ramakrishna, Ramayana, Golden Axe

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sever
    0.41
    Huh
    0.38
     بندی
    0.38
     lois
    0.37
    ر
    0.36
     cler
    0.36
     prati
    0.36
     बराबरी
    0.36
     eigenvector
    0.36
     ces
    0.35
    POSITIVE LOGITS
    я
    0.53
    जन
    0.51
     రోజుల
    0.51
    cienza
    0.48
    ggi
    0.47
     amulet
    0.47
    ुका
    0.47
    ម្លៃ
    0.46
    م
    0.46
    nails
    0.45
    Act Density 0.009%

    No Known Activations