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

    Neuronpedia

    INDEX
    Explanations

    references to the film industry and discussions about movies

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

    best short

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    …»
    -0.53
    ...»
    -0.52
    </blockquote>
    -0.50
    });*/
    -0.49
    })*/
    -0.48
    ...}
    -0.47
    >-->
    -0.46
    httphttps
    -0.46
    ...");
    -0.46
    );*/
    -0.46
    POSITIVE LOGITS
    こちらも
    0.63
    AsUp
    0.56
     underrated
    0.53
     Мексичка
    0.53
    LLocation
    0.52
    хьтан
    0.52
    ロウィン
    0.52
    AndEndTag
    0.52
    featureID
    0.52
    こちらは
    0.52
    Act Density 0.025%

    No Known Activations