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

    Neuronpedia

    INDEX
    Explanations

    specific compound terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     glued
    0.37
    俯
    0.36
    麋
    0.36
    पु
    0.35
     GW
    0.35
    concrete
    0.35
     "
    0.35
    SP
    0.35
    след
    0.35
     concrete
    0.35
    POSITIVE LOGITS
    ွင်း
    0.45
     antwort
    0.41
     awarding
    0.41
     quyền
    0.40
     asas
    0.40
    wner
    0.39
     অনুর
    0.39
     onların
    0.39
    ছাই
    0.39
     Evaluation
    0.38
    Act Density 0.000%

    No Known Activations