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

    Neuronpedia

    INDEX
    Explanations

    umbrella

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _training
    -0.07
    jin
    -0.07
     Jin
    -0.06
     minced
    -0.06
    _ON
    -0.06
     Languages
    -0.06
     Jason
    -0.06
    382
    -0.06
    Jason
    -0.06
    _Position
    -0.06
    POSITIVE LOGITS
     umbrella
    0.15
     umb
    0.08
     Umb
    0.08
     supplemental
    0.08
     UM
    0.07
    rella
    0.07
    rellas
    0.07
     retali
    0.07
     müda
    0.07
    _PROM
    0.07
    Act Density 0.002%

    No Known Activations