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

    Neuronpedia

    INDEX
    Explanations

    Cloud, Node, Learning, IBM, Determination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.65
     h
    0.59
    "),
    0.59
    ↵
    0.57
     H
    0.57
     The
    0.56
     A
    0.54
     G
    0.53
     st
    0.51
    "
    0.51
    POSITIVE LOGITS
     遅く
    1.34
     disponibile
    1.25
    が存在
    1.19
     abbastanza
    1.18
     parvenir
    1.18
     ortaya
    1.17
     respal
    1.16
     diejenigen
    1.15
     disponibili
    1.15
    ในช่วง
    1.14
    Act Density 0.121%

    No Known Activations