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

    Neuronpedia

    INDEX
    Explanations

    markup or syntax-related elements, particularly in programming and documentation formats

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

    mathematical and code-like structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    writeFieldEnd
    -0.82
     useAppContext
    -0.82
     Italijani
    -0.79
    Personendaten
    -0.77
     Biôgrafia
    -0.77
    AutoField
    -0.74
     мәкал
    -0.74
    <pad>
    -0.73
    <unused17>
    -0.73
    <unused19>
    -0.73
    POSITIVE LOGITS
    })*/
    0.29
    أ
    0.29
    Còn
    0.28
    ↵↵
    0.28
    </thead>
    0.25
    Ắ
    0.25
    La
    0.25
    ️
    0.25
    مصادر
    0.25
    })));
    0.24
    Act Density 0.000%

    No Known Activations