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

    Neuronpedia

    INDEX
    Explanations

    naming concepts and their attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ?
    0.43
    !
    0.43
    あくまで
    0.41
    "
    0.41
     degenerative
    0.41
     immun
    0.41
     epigenetic
    0.40
     marinade
    0.40
    immune
    0.39
     phyt
    0.39
    POSITIVE LOGITS
    рт
    0.45
     años
    0.45
    ಿಗೆ
    0.44
     যশোরে
    0.44
    සිය
    0.43
    یس
    0.43
     关闭
    0.43
    Мар
    0.42
     passos
    0.41
    Го
    0.41
    Act Density 0.059%

    No Known Activations