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

    Neuronpedia

    INDEX
    Explanations

    properties of concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     TMP
    0.42
     thermoplastics
    0.42
    vidia
    0.39
    anta
    0.38
     Janeiro
    0.38
     ordenador
    0.38
     ঠ
    0.37
     webdriver
    0.37
    ici
    0.37
    வில்
    0.37
    POSITIVE LOGITS
    成績
    0.38
     мыкты
    0.38
     실패
    0.37
    ͯ
    0.36
     powodu
    0.35
    ี
    0.35
     instability
    0.35
     degrade
    0.35
     ویژگی
    0.35
     dismal
    0.35
    Act Density 0.001%

    No Known Activations