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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    .Scheme
    -0.07
    antro
    -0.07
    ndl
    -0.06
    >
↵
↵
↵
    -0.06
    นวน
    -0.06
     fabrics
    -0.06
     setSize
    -0.06
    �
    -0.06
    Full
    -0.06
    POSITIVE LOGITS
    CAPE
    0.07
    /MPL
    0.06
     Golf
    0.06
     serbest
    0.06
     tournaments
    0.06
     Merrill
    0.06
    擊
    0.06
     PORT
    0.06
    stricted
    0.06
    .Assertions
    0.06
    Act Density 0.073%

    No Known Activations