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

    Neuronpedia

    INDEX
    Explanations

    alternatives, choices, or presentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     erhalten
    0.43
    preserve
    0.42
     preserves
    0.42
    ガイド
    0.40
    jej
    0.40
     preserve
    0.40
    podob
    0.39
    ართველ
    0.37
    jeff
    0.37
    쾅
    0.37
    POSITIVE LOGITS
    或者是
    0.49
    或者
    0.43
     situações
    0.42
     apresentação
    0.42
    或是
    0.42
     presentación
    0.40
     或者
    0.39
    的内容
    0.39
     resumo
    0.39
     oppure
    0.39
    Act Density 0.001%

    No Known Activations