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

    Neuronpedia

    INDEX
    Explanations

    forms of the verb "to be" in various contexts

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

    states of being or causality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     paille
    -0.41
    Ran
    -0.37
     STUD
    -0.37
    })*/
    -0.36
    writerow
    -0.36
     *)&
    -0.36
     Wand
    -0.35
     Vest
    -0.35
    フジテレビ
    -0.35
     Existing
    -0.35
    POSITIVE LOGITS
     kasarigan
    0.61
     kän
    0.54
     مشين
    0.54
     certainly
    0.53
     evident
    0.52
     fatores
    0.51
     contraste
    0.50
     undoubtedly
    0.50
     verkligen
    0.50
    GIVEREF
    0.49
    Act Density 0.069%

    No Known Activations