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

    Neuronpedia

    INDEX
    Explanations

    instances of media outlet names and their associated formatting

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

    closing parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     snippetHide
    -0.75
    脚注の使い方
    -0.73
    GraphicsUnit
    -0.65
    -0.65
     يتيمه
    -0.64
    tanleria
    -0.62
     desmotivaciones
    -0.62
    majánló
    -0.58
     صوتيه
    -0.57
    ۜ
    -0.56
    POSITIVE LOGITS
    )
    0.44
    '/',
    0.41
     TV
    0.40
    })();
    0.40
    ]]);
    0.39
    }');
    0.39
    ']>
    0.38
    FP
    0.38
    '}}
    0.37
     ']
    0.37
    Act Density 0.005%

    No Known Activations