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

    Neuronpedia

    INDEX
    Explanations

    GitHub Apps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    opcao
    0.46
    learn
    0.46
     option
    0.43
     opções
    0.41
    MENU
    0.40
     opciones
    0.40
     opcao
    0.40
    オプション
    0.39
     astronomers
    0.39
    options
    0.39
    POSITIVE LOGITS
     хорошее
    0.45
     common
    0.43
     Common
    0.42
     चिप
    0.41
     unnecessarily
    0.40
    Common
    0.38
     almaya
    0.38
    engel
    0.37
    ስማ
    0.37
     хорошие
    0.37
    Act Density 0.003%

    No Known Activations