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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    번째
    -0.07
    官方
    -0.07
     ANAL
    -0.06
     illustrations
    -0.06
    véd
    -0.06
    uges
    -0.06
     soils
    -0.06
     Calls
    -0.06
     haline
    -0.06
    veç
    -0.06
    POSITIVE LOGITS
    .$
    0.07
    Based
    0.07
    ...↵↵↵↵↵↵
    0.06
     burner
    0.06
     polled
    0.06
    Plain
    0.06
    334
    0.06
    disposed
    0.06
    (tile
    0.06
     )}↵↵
    0.06
    Act Density 0.098%

    No Known Activations