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

    Neuronpedia

    INDEX
    Explanations

    multilingual noun phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     der
    1.21
    μός
    1.16
    Der
    1.15
    формация
    1.07
    ляция
    1.01
     großer
    1.00
     Der
    0.99
    ικός
    0.98
    μος
    0.97
     dieser
    0.96
    POSITIVE LOGITS
     את
    3.38
     را
    2.66
     einen
    2.31
     την
    2.30
    тельную
    1.86
     τὴν
    1.86
    数を
    1.86
    жную
    1.85
    物を
    1.84
    情報を
    1.83
    Act Density 0.096%

    No Known Activations