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

    Neuronpedia

    INDEX
    Explanations

    societal biases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Burgundy
    1.14
     Chile
    1.13
    odigd
    1.12
    rugula
    1.07
    চৈত
    1.05
    Chile
    1.05
    मध्यप्रदेश
    1.04
    🦅
    1.04
     کنکریاں
    1.04
    Councillor
    1.04
    POSITIVE LOGITS
    t
    1.69
    tio
    1.15
    fabrik
    1.10
     arquivos
    1.10
     dimers
    1.09
     autom
    1.08
    бед
    1.07
     industriel
    1.06
     deva
    1.06
     जिन
    1.06
    Act Density 0.001%

    No Known Activations