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

    Neuronpedia

    INDEX
    Explanations

    forms of the verb "to be" in various languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    linking verbs in many languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.56
     ſtate
    -0.49
     Cæsar
    -0.48
     Jefus
    -0.48
     medes
    -0.47
    Geplaatst
    -0.47
    揄
    -0.46
     coscienza
    -0.46
     يتيمه
    -0.46
    Географиясе
    -0.45
    POSITIVE LOGITS
     is
    0.73
     are
    0.62
     ISNI
    0.60
     adalah
    0.58
     está
    0.53
     è
    0.53
     είναι
    0.52
    是
    0.51
    は
    0.49
    énario
    0.48
    Act Density 0.014%

    No Known Activations