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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Weight
    -0.07
     herb
    -0.07
     nových
    -0.07
    .strict
    -0.07
     complication
    -0.07
     والتي
    -0.07
    &id
    -0.07
     Bail
    -0.06
    เบ
    -0.06
    nerg
    -0.06
    POSITIVE LOGITS
    (IL
    0.07
    INSTALL
    0.06
    >?
    0.06
    ']),
    0.06
    aylight
    0.06
    ((&___
    0.06
    >;↵↵
    0.06
    869
    0.06
     topLevel
    0.06
     """
↵
↵
    0.05
    Act Density 0.003%

    No Known Activations