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

    Neuronpedia

    INDEX
    Explanations

    Count followed by numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IRCONIUM
    0.39
    CUSSION
    0.32
    OLYBD
    0.32
    疾患
    0.32
    OLYBDENUM
    0.32
    ClFN
    0.32
     glycos
    0.31
    Imidazole
    0.31
    positroid
    0.31
    Hydrochloride
    0.31
    POSITIVE LOGITS
     Finance
    0.38
     data
    0.35
     Data
    0.35
     Hola
    0.35
     Company
    0.34
     Hello
    0.34
    ↵
    0.34
     News
    0.33
     Marketing
    0.33
     was
    0.32
    Act Density 2.924%

    No Known Activations