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

    Neuronpedia

    INDEX
    Explanations

    punctuation and significant terms in a technical context

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

    mathematical expressions and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Италијани
    -0.47
    )))),
    -0.47
    }}},
    -0.42
     &___
    -0.40
    "}},
    -0.40
    })));
    -0.39
    就这样
    -0.38
    ])]
    -0.38
    exitRule
    -0.38
    HomeAsUpEnabled
    -0.37
    POSITIVE LOGITS
    ParallelGroup
    1.36
    saraba
    0.65
    encodeWith
    0.61
     ModelExpression
    0.54
    WaitGroup
    0.52
     يتيمه
    0.51
    withIdentifier
    0.50
    EDEFAULT
    0.50
    styleType
    0.48
    Климат
    0.47
    Act Density 0.000%

    No Known Activations