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

    Neuronpedia

    INDEX
    Explanations

    phrases related to relationships and a sense of obligation

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

    describes purpose or characteristic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surla
    -0.75
     informée
    -0.62
     للاسماء
    -0.56
    WritableDatabase
    -0.54
    脚注の使い方
    -0.54
     Exactos
    -0.53
     houſe
    -0.51
    #+#
    -0.50
    sistor
    -0.50
    CloseOperation
    -0.50
    POSITIVE LOGITS
    rungsseite
    0.43
    Descripció
    0.40
    }],
    0.36
    Marshaller
    0.36
    ])).
    0.36
    %"),
    0.35
    )++;
    0.35
    >--}}
    0.35
     könne
    0.35
    Unmarshaller
    0.34
    Act Density 1.284%

    No Known Activations