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

    Neuronpedia

    INDEX
    Explanations

    pronouns related to the first-person perspective

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

    Ichimura academic citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    batore
    -0.61
    }></
    -0.56
     }}"></
    -0.56
     ExecuteAsync
    -0.55
    ]?.
    -0.54
    er
    -0.53
    ]").
    -0.51
    )?.
    -0.51
    lossenen
    -0.50
    +":
    -0.50
    POSITIVE LOGITS
     Ich
    1.32
    Ich
    1.30
     ich
    1.15
     ICH
    0.84
     Ik
    0.68
    Ik
    0.66
     I
    0.63
     ik
    0.60
    Jeg
    0.57
    ฉัน
    0.57
    Act Density 0.001%

    No Known Activations