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

    Neuronpedia

    INDEX
    Explanations

    specific determiners or pronouns associated with identity

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

    the very, same, entire, first

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pravi
    -0.35
    rxjs
    -0.34
     nearby
    -0.31
     lagi
    -0.30
     εκ
    -0.29
    ที
    -0.28
     veliko
    -0.28
    ให
    -0.27
     kollu
    -0.27
     alway
    -0.27
    POSITIVE LOGITS
    +#+#
    0.73
    rungsseite
    0.71
    ſicht
    0.68
    ロウィン
    0.66
     tartalo
    0.66
     autorytatywna
    0.65
     zwiſchen
    0.65
    0.65
     パンチラ
    0.65
    OrNil
    0.65
    Act Density 0.046%

    No Known Activations