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

    Neuronpedia

    INDEX
    Explanations

    typescript code examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     производство
    0.51
     али
    0.51
    messaging
    0.49
     दर्ज
    0.48
    thresh
    0.48
     zwölf
    0.47
    seeded
    0.46
     числі
    0.46
    haired
    0.46
     نہيں
    0.46
    POSITIVE LOGITS
     Salt
    0.46
     Dasar
    0.45
     Am
    0.43
     Shayari
    0.42
     os
    0.42
     Arctic
    0.42
     Angular
    0.42
     Tennyson
    0.42
     Ke
    0.41
     Fundamentals
    0.41
    Act Density 0.001%

    No Known Activations