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

    Neuronpedia

    INDEX
    Explanations

    time it takes for events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ставки
    0.37
    ible
    0.35
    uj
    0.34
    kubernetes
    0.32
    ურთ
    0.30
    릿
    0.29
    ried
    0.29
     simplifying
    0.29
     basics
    0.29
    ets
    0.29
    POSITIVE LOGITS
     achieve
    0.42
     accomplish
    0.38
     occur
    0.38
     மூலம்
    0.37
    च्चय
    0.37
     mencapai
    0.36
     werde
    0.35
     എന്നിവ
    0.35
     rozwoju
    0.35
     displayName
    0.35
    Act Density 0.001%

    No Known Activations