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

    Neuronpedia

    INDEX
    Explanations

    references to self-identity and personal introspection

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

    own, myself, yourself, too

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     poži
    -0.30
    czy
    -0.29
     consent
    -0.28
     permits
    -0.28
     rör
    -0.27
    นิ
    -0.27
    入
    -0.27
    出会
    -0.26
    ểu
    -0.26
     préférence
    -0.26
    POSITIVE LOGITS
    parsedMessage
    0.71
    自分も
    0.68
    цездатний
    0.64
     kaarangay
    0.64
    UnusedPrivate
    0.60
     betweenstory
    0.59
     dAtA
    0.59
    AccessorTable
    0.59
    __(/*!
    0.59
    Cyfarwyddwr
    0.57
    Act Density 0.253%

    No Known Activations