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

    Neuronpedia

    INDEX
    Explanations

    expressions of acknowledgment or admission, particularly related to conceding defeat or recognizing facts

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

    admitting or conceding points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.40
    Portail
    -0.36
    fillType
    -0.35
     behulp
    -0.33
     rast
    -0.32
    printList
    -0.32
     munici
    -0.31
     filmo
    -0.31
     aerolí
    -0.30
     Erik
    -0.30
    POSITIVE LOGITS
     concede
    1.88
     conceded
    1.88
     conceding
    1.77
     concedes
    1.64
     conced
    0.91
     admitting
    0.86
     admits
    0.85
     admit
    0.83
     Admit
    0.83
     cede
    0.82
    Act Density 0.005%

    No Known Activations