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

    Neuronpedia

    INDEX
    Explanations

    math symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     minWidth
    -0.07
    rió
    -0.06
    사무
    -0.06
     título
    -0.06
     straightforward
    -0.06
     працю
    -0.06
     imper
    -0.06
     ώ
    -0.06
    गर
    -0.06
    >y
    -0.06
    POSITIVE LOGITS
    terraform
    0.07
     devam
    0.07
    exclude
    0.07
    _CUSTOMER
    0.06
     singapore
    0.06
     cash
    0.06
    Gs
    0.06
    _Ex
    0.06
     BST
    0.06
    >Hello
    0.06
    Act Density 0.002%

    No Known Activations